- Additional video files from the 2008 CPES workshop are now available. These files include sessions with CPES principal investigators and researchers, as follows:
- James Jackson (MOV 258MB), National Survey of American Life (NSAL)
- Gilbert Gee (MOV 130MB), National Latino and Asian American Survey (NLAAS)
- Ronald Kessler (MOV 274MB), National Comorbidity Survey, Replication (NCS-R)
- Hector Gonzalez (MOV 244MB), National Latino and Asian American Survey (NLAAS)
- A *summer workshop* about CPES will be held June 16-18, 2008 in Ann Arbor, pending funding. Enrollment in the course is limited to 25 participants selected for their methodological qualifications and their ability to contribute to the substantive area. Applications must be received by April 28 and include a vita and cover letter summarizing research interests, course objectives, and experience. Instructors will include those most familiar with CPES and material will cover instrumentation, diagnostic algorithms and other constructed variables, sample design and weighting, techniques for the appropriate analysis of complex sample survey data, and concrete analytic examples. The CPES investigators will be invited to join a discussion in-person and via video-conference. There is no cost to attend the workshop.
- No. Please note that few screening questions (SC2, SC2.1, SC2.2, SC2.3, SC8.1, SC8.2) were removed during the NCS-R data collection in 2001-2002. The CPES released dataset included valid answers provided by NCS-R respondents who were interviewed before these questions were removed and NCS-R respondents who were not interviewed with these questions were counted as "Missing (System)" on these questions. Below is the list of questions and please click links to view the summary statistics and/or frequencies:
- SC2 - How long have you lived at your current address?
- SC2.1 - About how many years have you lived in this state?
- SC2.2 - About how many miles do you currently live from the place where you were raised during most of your childhood?
- SC2.3 - How many different houses or apartments have you lived in since the age of 18?
- SC8.1 - How would you rate your overall physical health -- excellent, very good, good, fair, or poor?
- SC8.2 - How would you rate your overall mental health -- excellent, very good, good, fair, or poor?
- No. Some questions were asked in one study and not in the others. Questions not asked of all respondents include the following:
- Age under 45: The Attention Deficit/Hyperactivity (AD), Oppositional Defiant Disorder (OD), and Conduct Disorder (CD) sections were administered only to individuals who were under the age of 45.
- The National Comorbidity Survey Replication (NCS-R) had two Parts: Part 1 included a core diagnostic assessment of all 9,282 respondents. Part 2 was administered only to 5,692 of the 9,282 Part 1 respondents, including all Part 1 respondents with a lifetime disorder plus a probability subsample of other respondents. See the Final Weights section of the User Guide section of About CPES for an explanation of the two parts and the implications for weighting analyses.
- The National Survey of American Life (NSAL) Black Caribbean sample had some questions that no one else had.
- The National Survey of American Life (NSAL) had several sections which were not administered to the White sample. See below for a list of sections skipped if the NSAL respondent was White.
Question Numbers Mental Disorder Administered to Whites DP1-DP88 Depression X M1-M54 Mania X PD1-PD66 Panic Disorder X SO1-SO40 Social Phobia X AG1-AG39 Agoraphobia X GA1-GA51b Generalized Anxiety Disorder X SD0-SD29 Suicidality SU1-SU120b Alcohol and Other Substance Abuse and Dependence PH1-PH175 Pharmacoepidemiology PEA40-PEA83 Personality Disorders PT1-PT281 Post-Traumatic Stress Disorder NSD1-NSD2 30-Day Symptoms TB1 Tobacco Use EA1-EA43 Eating Disorders: Anorexia and Bulimia PR1-PR19a Pre-Menstrual Dysphoric Disorder O1-O17 Obsessive-Compulsive Disorder PS1-PS10 Psychosis Screen GM1-GM6 Gambling FH1-FH39 Family History AD1-AD51 Attention-Deficit/Hyperactivity Disorder OD1-OD27 Oppositional Defiant Disorder CD1-CD40 Conduct Disorder SA1-SA50b Separation Anxiety SR1-SR135 Services
- Yes. All of the public-use data have passed through confidentiality reviews according to standard social research guidelines and procedures and have been available for secondary analysis.
The Latino sample in the NSAL is part of the Afro-Caribbean sample. Therefore, NSAL required that all Latinos in the NSAL self-report as being of Black race and of Caribbean descent. The Latino sample in the NLAAS could have self-reported being of any race.
Yes, they are different in one very important aspect: The NCS-R White sample is representative of non-Latino Whites in the U.S., whereas the NSAL Whites are representative of non-Latino Whites in the U.S who live in households located in census tracts and block groups with a 10% or greater African American population. NSAL Whites are unique in that their selection rate was based on the African American distribution, that is, their probability of selection increased as the density of African Americans increased in the block group. This NSAL White sample was designed to be optimal for comparative analyses in which residential, environmental, and socioeconomic characteristics are controlled.
- There is a race/ethnicity variable in CPES. It does not contain the number of Native Americans because of possible confidentiality issues. The restricted-use version of NCS-R includes this information but the actual number of respondents in this category may be insufficient to do any meaningful analyses.
- Age of onset and recency were also included for each disorder. In addition, Sheehan disability measures were created and included for each disorder that includes the Sheehan questions.
- Because of the importance of maintaining respondent confidentiality, we did not release the census tract, city, or county in which the respondent lived at the time of the interview in the public-use files. If you do want to access geographic identifiers you must contact email@example.com and consult ICPSR?s instructions on Applying for Restricted Data and complete the forms as outlined. The geographic identifiers we have are at the Federal Information Processing Standard (FIPS) county level. You could request the restricted-use data which has county code and then merge county Census data. You can find more information on this in the Weighting section of About CPES.
- Because of the importance of maintaining respondent confidentiality, we did not release the state in which the respondent lived at the time of the interview. The geographic identifiers we have are at the Federal Information Processing Standard (FIPS) county level. You could request the restricted-use data which has county code and then merge county Census data. You can find more information on this in the Weighting section of Using CPES.
- Yes. Please see items NCS-R (CC50_4), NLAAS (CC50_4) and CPES (V04334), which ask the respondents if they are covered by Medicaid (Are you covered by [(STATE NAME FOR MEDICAID)], the government assistance program for people in need?). See these variables in the Chronic Conditions section of the Interactive Codebook.
- Yes. You will need to make this request through the SAMDHA Disclosure Committee which makes decisions regarding release of the restricted-use data through ICPSR. You can request the restricted-use version through the Applying for Restricted-Use Data process that includes signing an Agreement and providing a data protection plan.
- Recoded variables were specifically created for the public-use files. There are no original codes in any of the restricted-use files because a considerable amount of cleaning and processing was performed on the data collected from respondents in order to create the recodes. The ?original? codes themselves are not available.
- Unfortunately, we are unable to send you these materials. These are materials associated with the World Health Organization?s CIDI Training Centre and were provided to ICPSR trainees under a special agreement. If you are interested in attending a CIDI training, please contact: firstname.lastname@example.org. Please note, however, that considerable Training Resources are available on the CPES Website.
- Yes, you may. If the computer will be connected to a network, your data protection plan needs to indicate how the data will be safeguarded. In these cases, we strongly suggest that you encrypt the data if it sits on the network, or that you load the data from the CD every time you do analysis.
- Unfortunately, the response options in CPES may never be defined to the level that you want. It was up to the respondent to determine whether they received services in either mental health setting or human service settings.
- We are sorry but the volume of questions of this nature exceeds the resources we have available for these requests.
- We are sorry but the volume of questions of this nature exceeds the resources we have available for these requests.
- Two of the category labels were mislabeled on the following variable:
V09346 (yrsinusa5cat) - Number of Years in US 5 Categories
Value 1 should be "Less than 6 yrs" (currently shown as "Less than 5 yrs")
Value 2 should be "6-10 yrs" (currently shown as "5-10 yrs")
This change impacts the CPES, NLAAS and NSAL variable. Please be aware of this change when using the interactive documentation and public release datasets.
- Because of an eight-character limit in the length of variables names in the software that created the datasets used by SDA and that users download, there are some discrepancies in variable names between the CPES interactive documentation and the datasets for NCS-R, NSAL, and NLAAS. Please consult the last part of the data processing notes section of the CPES User Guide for the complete list.
Dear CPES users:
- The 5th category should be TAGALOG: 16 respondents.
- The 6th category should be VIETNAMESE: 119 respondents.
We apologize for the mistakes made during the data processing!
Dear CPES users, the Vairable Search function is available now, please visit this Web page: http://www.icpsr.umich.edu/icpsrweb/CPES/search.jsp.
- The 2001?2 NCS survey program included two major survey components: the NCS-R replication study and the National Comorbidity Survey-2 reinterview study. The NCS-2 was a longitudinal study that attempted to recontact and reinterview all surviving respondents from the 1992 National Comorbidity Survey (Kessler et al., 1994). The focus of the discussion here is on the NCS-R, a new cross-sectional sample survey of the U.S. adult population. NCS and NCS-R are indeed two completely separate cross-sectional surveys that cannot be linked
- All three surveys which comprise CPES required informed consent from respondents but only NLAAS required written informed consent. NCS-R and NSAL required oral consent. For more information, please refer to this article:The development and implementation of the National Comorbidity Survey Replication, the National Survey of American Life, and the National Latino and Asian American Survey (p 241-269). Beth-Ellen Pennell, Ashley Bowers, Deborah Carr, Stephanie Chardoul, Gina-qian Cheung, Karl Dinkelmann, Nancy Gebler, Sue Ellen Hansen, Steve Pennell, Myriam Torres.
- No. Since CPES was collected through the survey process, they did not fall under HIPPA privacy rules which govern data held by insurance companies and health care providers.
- We did not have a variable for severity distribution in the CPES; rather, we used a simulation model that generated multiply imputed predicted probabilities of each value on the severity distribution to the CPES data. We do not have user-friendly documentation of this simulation, and we are not set up to provide consultation on the statistical methods required to implement this approach. As a result, we are not making the simulation programs available in our public data release. However, it is possible to develop the same logic based on the information provided in the NEJM and Archives papers.
- We did not include these variables in the CPES for three reasons: the documentation needed would have been rather extensive, we are not set up to provide consultation on the statistical methods required to implement this approach, and some researchers would have preferred to create these measures using different criteria. However, it is possible to develop the same logic based on the information provided in the NEJM and Archives papers.
- You must always use complex survey design measures in order to estimate the variance correctly. However, when the sample size is under 200, the data are distributed more like a simple random sample distribution. Only in these situations would it be acceptable to use the regular software commands that treat the small sample as a simple random sample.
- You must always use weights. You must also use Complex Survey measures in order to estimate the variance correctly. However, when the sample size is under 200, the data are distributed more like a simple random sample distribution. Only in these situations, it would be acceptable to use the regular software commands that treat the small sample as a simple random sample. See CPES Weights Chart for more information.
- It is not a requirement to use a stand-alone computer. If the computer will be connected to a network, your data protection plan needs to indicate how the data will be safeguarded. In these cases, we strongly suggest that you encrypt the data if it sits on the network, or that you load the data from the CD every time you do analysis.
- There were 10 NSAL variables that were inadvertently omitted from the CPES public release datasets. These are available for download in a supplemental file. These are:
V07557 (D_BIPOLARI30) DSM-IV Bi-Polar I (30Day)The supplemental data can be merged to the main CPES public release dataset using CPESCASE, CPESPROJ and VERSION. A second version of the CPES public release dataset has been released (Version=2 for all records) and the supplemental file should only be merged to this version of the dataset.
V07561 (D_BIPOLARII30) DSM-IV Bi-Polar II (30Day)
V08217 (GAD_ONI) ICD Generalized Anxiety Disorder Onset
V08221 (GAD_RECI) ICD Generalized Anxiety Disorder Recency
V08374 (I_GAD12) ICD Generalized Anxiety Disorder(12Mo)
V08375 (I_GAD30) ICD Generalized Anxiety Disorder(30Day)
V08377 (I_GADH12) ICD Generalized Anxiety Disorder w/hier(12Mo)
V08378 (I_GADH30) ICD Generalized Anxiety Disorder w/hier(30Day)
V08528 (ICD_GAD) ICD Generalized Anxiety Disorder(LifeT)
V08529 (ICD_GADH) ICD Generalized Anxiety Disorder w/hier(LifeT)
- Yes, a faculty member must be the principal investigator and you would be listed as supplemental research staff.
- All of the system missing cases are due to conditions in which a particular respondent did not receive the question but the reason could vary from case to case.
- In the navigation bar, you'll see a link titled Login/Account Info [http://]. If you've already logged in, this will take you to a list of MyData links. One of those is Edit Account Settings [http://]. Here you can change your password, email address, or any other information you have previously provided.
- CPES does not have any variable that captures all disorder conditions. For creating a variable that captures any disorder from NCS-R data set, please refer to: Kessler, R. C., Chiu, W. T., Demler, O., et al. (2005). Prevalence, severity, and comorbidity of 12-month DSM-IV disorders in the National Comorbidity Survey Replication. Arch Gen Psychiatry, 62, 617-627.
- In addition to the CPES Publications, you may go to the following links to obtain the list of publications for each of the studies.In addition, two issues of the International Journal of Methods in Psychiatric Research were devoted to the CPES project. You can read the articles in those issues at:
- The personality items can be found at Interactive Codebook and cover PEA40 - PEA49 (Zuckerman Social Desirability) and PEA50-PEA83 (IPDE).However, the IPDE scale was the scale used in the Lenzenweger paper. Using the clinical interview NCS-R came up with the best predictors of 6 IPDE diagnoses and generated predicted probabilities for each of the full part 2 NCS-R samples. However, NCS-R did not make the personality disorder diagnostic variables public since they are NCS-R has 10 multiply imputed values for each disorder (generated 10 yes/no values from the predicted probabilities).
- You can view the universe of respondents for each question in the separate surveys bychoosing the ?View Universe? link on the variable pages in the Interactive Codebook section of the CPES Web site. The actual questionnaires for each survey are also available through the links to each of the project sites on the CPES home page. These questionnaires also have routing instructions included.
- The SESTRAT within SECLUSTR values are currently set up as strata with a value of either 1 or 2 in the cluster or SECU variable. They are unique records within those variables but Mplus requires a unique cluster value within the strata. It is easy to just renumber and create new variables.For example, in a data set with 100 records and SESTRAT ranges from 1-20 (just an example) and there are values of 1 or 2 in SECLUSTR then they could be renumbered to NEWSTRAT in 1-20 and NEWCLUSTR in 1 to 100 the total number in each of the NEWSTRAT variables.Old Strata, Old Cluster, New Strata, New Cluster1 1 1 11 1 1 21 2 1 31 2 1 42 1 2 52 2 2 6Etc. ?20 2 20 100Mplus requires unique strata/cluster combinations so this method allows you to define the records within Strata/PSU without changing the basic complex sample variable structure or meaning. The user could use the define statement in Mplus or do this outside of Mplus in the software of choice.
- The questions asked in the three separate surveys that comprise CPES were all administeredthrough Computer-Assisted Personal Interviewing (CAPI) software so the routing of the questions was often quite complex. The actual questionnaires for each survey are also available through the links to each of the project sites on the CPES home page. These questionnaires also have routing instructions included.
- SPSS for Macintosh, Version 6.1.1 and earlier versions, do not recognize UNIX linefeed characters. Macintosh users must change these characters manually before reading the file into SPSS. We suggest using a text editor, such as BBEdit, to read the data file, and then saving it as a Macintosh file. This will replace the UNIX linefeeds with Macintosh carriage returns that SPSS for the Macintosh can understand. BBEdit is available from the Bare Bones Software Web site. BBEdit and most other text editors are unable to read very large files, depending on the amount of memory available. For larger files, we suggest using text conversion software, such as TextToMac, that may be less memory-intensive. You can download texttomac1.2.hqx from the University of Michigan archive .
- Setup files (also known as control cards or data definition statements) contain the syntax or program code to read columnar ASCII data into a statistical package. For detailed instructions on how to use SAS, SPSS, or Stata setup files in a Windows environment, see:
Note: In order to successfully use setup files, you must know the exact location (i.e., full pathname, such as C:\My Documents\Data) and filename (e.g., 09999-0001-Data.txt) of the files that you downloaded.
- How do I use a SAS setup file to import ASCII data?
- How do I use an SPSS setup file to import ASCII data?
- How do I use a Stata setup file to import ASCII data?
- CPES files distributed via the Internet were compressed using Windows Zip data compression software. Files compressed using WinZip have the .zip file name extension. Users who download compressed files will have to decompress the files before using them.Please note that files downloaded prior to November 29, 2004, may have the Gzip compression format.WindowsWindows XP has a built-in decompression tool that decompresses .zip files. Users with other Windows versions may need to download the utility from the WinZip Web site.WinZip and the Saved Files UtilityWinZip users (and those who use the built-in decompression tool in Windows XP), should be aware that WinZip has two ways to extract files: by using drag-and-drop and by choosing "Extract" from underneath the "Actions" menu. These two methods produce different results. If you use drag-and-drop, then you will only get the files...not the folders that enclose them. Hence you'll lose the hierarchy that CPES has set up (including folders that are titled with study names and data set names). If you use the "Extract" command from the "Actions" menu, then the folder hierarchy is preserved if 'Use Folder Names' is specified in the extraction dialog box.MacintoshFor Macintosh OSX users, decompression software is built into the operating system; you can open compressed files by double-clicking on the .zip file.If you're encountering problems with the MacOSX built-in decompression software, you may wish to download StuffIt Expander.UNIX/LinuxUsers in the UNIX/Linux environment can simply use the unzip command to decompress .zip files.Once you have the appropriate software on your local machine, follow the instructions supplied by your software to decompress the zipped files.
- Downloading data from the CPES Web site is easy. First find the study you want, and then click on the "download" link. The Download page will walk you through a series of steps:
- Select your statistical package, from the list of available packages. Some of our studies have "ready to go" files available; for others you'll need to download the ASCII data and setup files to make your own "ready-to-go" file.
- Select the data sets you wish to download. Many of our studies have only one data set, but the more popular ones tend to have multiple data sets.
- Add the files to your data cart using the "Add to Data Cart" button.
- You can choose to review the contents of your cart, and delete files if you wish by clicking on the "Review Data Cart" button.
- Finally, click on the button "Download Data Cart." This will download a zip file that contains all the files you requested. The appropriate documentation files are automatically added. If you don't know how to uncompress the zip file, take a look at "How do I decompress the files I download from your site?"
- Just go to the MyData login page [http://]. At the bottom of the page is a link titled Forgot your password [http://www.icpsr.umich.edu/cgi-bin/reqpw?path=CPES]? You'll be asked to enter your email address, and then a new password will be sent to you. After you get the email, you'll probably want to change your password [http://] to something easily remembered.
- The Interactive Codebook section on the CPES Web site provides the universe for each question, that is, the path for each question. Having said that, however, this is a complex set of questions made even more so by the fact that it is impacted by the long/short version of the NCS-R (see ?About CPES? for a description).The following logic is all online but varies by study.
You also indicate an interest in knowing whether the respondent was hospitalized for either a mental/emotional problem or a substance problem. There is no way to know this for sure, since SR2 lumps these all together. However, you could go back to each of the section-specific items and determine which were endorsed. The pitfall here is that respondent may give a positive answer at SR2 without having revealed a hospitalization in earlier sections -- in this case, you would never know the cause(s).
- NCS-R: All respondents who reach the Services (SR) section (i.e. are in Long Group) are asked SR2, regardless of their response to the "ever hospitalized" item in each of the earlier disorder sections. So, the missing cases at SR2 are only Short Group respondents (good news here is that if a respondent got as far as the "ever hospitalized" question in an earlier section, there is a very high likelihood that they would have been in the Long Group -- so you don't have to worry much about missing respondents who never reached the Services section).
- NSAL: There is an extra checkpoint (SR1) that evaluates the responses to all of the earlier "every hospitalized" items. If at least one YES response to the disorder-specific items, SR2 is not asked. So, for the missing SR2 cases, you will need to cross-reference all of the earlier items to see which one was endorsed (please also note that White respondents were not asked the Services section, so all Whites contribute to the missing values). The entire list of disorder-specific hospitalization items is included in the on-line documentation for SR1.
- NLAAS: Same structure as NSAL -- extra SR1 checkpoint that evaluates earlier disorder-specific hospitalization items. If at least one YES, SR2 is not asked. Again, the entire list of hospitalization items is listed at the SR1 online documentation.
Our data files are usually distributed as columnar ASCII files that consist of rows and columns of alphanumeric characters. Since ASCII data files are simply text files, they can be opened in any word processing program or Internet browser. However, the alphanumeric characters are not meaningful without the help of a codebook or setup files to identify the columns of the ASCII data file as particular variables.
This example illustrates how to interpret an ASCII data file for ICPSR 2737, Capital Punishment in the United States, 1973-1997.
The data file consists of 6,819 cases or observations, which in this example is inmates under sentence of death or those who were executed. Example 1 shows the first 10 lines of data in this file. The first observation, or line of data, is highlighted in red.
Example 1: The first case or line of data in the data file
The data file is a fixed format data file and is stored in a logical record length of 81. This means that each line is comprised of 81 characters. These 81 characters correspond to 37 variables or data items. Example 2 illustrates that each line of data in the file is 81 characters long.
Example 2: Each record is the same length (81 characters wide)
In order to know which columns comprise particular variables, it is necessary to refer to the codebook (PDF 234K). The following examples illustrate how to read the first ten variables from this ASCII data file, beginning with the first record (row) and counting from left to right:
V1-ICPSR STUDY NUMBER: This variable is positioned in column locations 1 through 4 and contains the value "2737" for each record. This value represents the 4-digit ICPSR archival study number assigned to this data collection.
Example 3: Variable 1 in Columns 1-4
V2-ICPSR EDITION NUMBER: This variable is positioned in column location 5 and contains the value "1" for each record. This value represents the ICPSR edition number assigned to the data collection.
Example 4: Variable 2 in Column 5
V3-ICPSR PART NUMBER: This variable is positioned in column location 6 and contains the value "1" for each record. This value represents the ICPSR part number assigned to the data file within the data collection.
Example 5: Variable 3 in Column 6
V4-ICPSR SEQUENTIAL ID: This variable is positioned in column locations 7 through 10 and contains the value "1" for the first record. This value represents the first sequential case identification number and is used to uniquely identify a given record in the data file.
Example 6: Variable 4 in Columns 7-10
V5-REPORT YEAR: This variable is positioned in column locations 11 through 14 and represents the reporting year. The first record, highlighted in red, contains the value "0", which represents a reporting year prior to 1973. The fifth record, also highlighted in red, contains the value "1973", which represents the actual year of the event.
Example 7: Variable 5 in Columns 11-14
V6-INMATE ID: This variable is positioned in column locations 15 through 18 and contains the value "8" for the first record. This value represents a four-digit inmate identification number.
Example 8: Variable 6 in Columns 15-18
V7-STATE: This variable is positioned in column locations 19 through 20 and contains the value "1" for all 10 records in this example. This value represents the FIPS state code for Alabama.
Example 9: Variable 7 in Columns 19-20
V8-Q3 SEX: This variable is positioned in column location 21 and contains the value "1" for the first 10 records. This code identifies the sex of these inmates as "male".
Example 10: Variable 8 in Column 21
V9-Q4A RACE: This variable is positioned in column 22 and contains the value "2" for the first record. This code identifies the race of this inmate as "Black".
Example 11: Variable 9 in Column 22
V10-HISPANIC ORIGIN: This variable is positioned column 23 and contains the value "2" for the first record. This code identifies the Hispanic origin of this inmate as "Non-Hispanic".
Example 12: Variable 10 in Column 23
To locate the column positions for the remaining variables for this study, see the codebook for CAPITAL PUNISHMENT IN THE UNITED STATES, 1973-1997.
This example illustrates that a visual interpretation of the data record is inefficient. Commercially available statistical software packages such as SAS, SPSS, and Stata are available to interpret data files and to subset the variables and or cases as needed.
This work is licensed under a Creative Commons Attribution-Noncommercial 3.0 United States License.
- The size of each uncompressed file in kilobytes will be found on the file manifest, and the size of your total download is listed in the View Cart screen and on each download page. Many data files are 100 megabytes or larger, and for that reason we provide files in compressed format. You will need to decompress the files using a decompression utility, such as WinZip®, in order to use the files. If you download the compressed file, you will need enough storage space to temporarily hold both the compressed and uncompressed files. Once you uncompress the file you can then remove the compressed version to save space on your local drive.
- Setup files contain the syntax or program code to read undelimited data (ASCII) into a statistical package. The instructions below demonstrate how to use SPSS setup files in a Windows environment. These instructions assume that you have already downloaded the ASCII data and SPSS setup file from the Internet. If you have a compressed version of a file, you will have to decompress it before using the setup files.Note: In order to successfully use setup files, you must know the exact location (i.e., full pathname, such as C:\My Documents\Data) and filename (e.g., da9999.txt) of the files that you downloaded.Instructions.
- Setup files contain the syntax or program code to read raw data (ASCII) into a statistical package. The instructions below demonstrate how to use SAS setup files in a Windows environment.These instructions assume that you have already downloaded the ASCII data and SAS setup file from the Internet. If you have a compressed version of a file, you will have to decompress it before using the setup file.Note: In order to successfully use setup files, you must know the exact location (i.e., full pathname, such as C:\My Documents\Data) and filename (e.g., da9999.txt) of the files that you obtained from ICPSR. Instructions.
- Setup files contain syntax or program code to read columnar ASCII data into a statistical package. The instructions below demonstrate how to use Stata setup files. Please note that while the examples and illustrations that follow depict Stata in a Windows environment, the steps and procedures are platform independent. Please see the appropriate Getting Started With Stata manual for operating system details.Getting Ready to Use Stata. These instructions assume that you have already downloaded the ASCII data and the Stata setup files from our Web site. If you have questions about downloading ICPSR data, please see How do I download data files?In addition, you must decompress the files you obtained from ICPSR before using the setup files. If you have questions about decompressing ICPSR files, please see How do I decompress the files I download from your site?Be sure to make a note of the exact location of the uncompressed files extracted from the download cart (file) you obtained from ICPSR as you will need to input that information into one of the setup files. The Stata Setup Components.
The instructions below cover how to install East Asian fonts on Windows XP SP2. You will need to have your SP2 install disc. If you're using a different operating system, you will need to contact the software's producer for support.
- Verify that you have the Windows XP SP2 installation disc.
- Close out of all applications (as you will have to restart at the end of installation).
- From the Start Menu, select Control Panels.
- Open the control panel titled Regional and Language Options.
- Select the middle tab, which is titled Languages.
- Click on the checkbox to the left of "Install files for East Asian languages."
- A pop-up will appear, informing you that installing these fonts will take up space on your hard drive. Click OK.
- Back at the control panel, click OK again to begin installation of the fonts.
- A pop-up window will appear asking you to insert the Windows XP SP2 installation disc. Insert the disc and click on OK.
- Wait patiently.
- After installation is complete, a pop-up window will appear asking you to restart your computer. Click on Yes.
- You're done. The Vietnamese and Chinese fonts are now installed on your computer.
If you have any trouble installing the fonts, please contact Microsoft.
- In the Data Collection section of About CPES, Table 8 shows for each survey the number of interviews, response rate, interview length (minutes), and average number of contacts per interview.The average interview length (minutes) for each CPES study was:
- The National Comorbidity Survey Replication (NCS-R) average interview length (minutes) was 126 minutes for the main respondent and 124 minutes for the second respondent in the household.
- The National Survey of American Life (NSAL) average interview length (minutes) was 145 minutes.
- The National Latino and Asian American Study (NLAAS) average interview length (minutes) was 161 minutes for the main respondent and 152 minutes for the second respondent in the household.
- In the Data Collection section of About CPES, Table 8 shows for each survey the number of interviews, response rate, interview length (minutes), and average number of contacts per interview.The average numbers of contacts per interview made in each survey were:
- The National Comorbidity Survey Replication (NCS-R) average number of contacts per interview was 7.1 for the main respondent and 4.7 minutes for the second respondent in the household.
- The National Survey of American Life (NSAL) average number of contacts per interview was 7.4.
- The National Latino and Asian American Study (NLAAS) average number of contacts per interview was 9.2 for the main respondent and 11.6 for the second respondent in the household.
- In the Data Collection section of About CPES, Table 8 shows for each survey the number of interviews, response rate, interview length (minutes), and average number of contacts per interview.The CPES joins three nationally representative surveys and there are 20,013 cases in the CPES:
According to NSAL variable ?RANCEST? there are 1,438 Afro Caribbeans and 183 Hispanics; however, the literature published on the NSAL reports 1621 Afro Caribbeans, they include the 183 Hispanics. The RANCEST recode is described in the Data Processing Notes on CPES Web site. The 183 individuals labeled as ?All Other Hispanics? comprise black Caribbeans from the British Virgin Islands, Guadeloupe, the Dominican Republic, Panama, Costa Rica, Nicaragua, and Honduras.
Alegria, M., Jackson, J. S., Kessler, R. C., & Takeuchi, D. Collaborative Psychiatric Epidemiology Surveys (CPES), 2001-2003 [UNITED STATES] [Computer file]. ICPSR20240-v5. Ann Arbor, MI: Institute for Social Research, Survey Research Center [producer], 2007. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2008-06-19. doi:10.3886/ICPSR20240.
- The suggested study description or metadata record for CPES is:
Alegria, M., Jackson, J. S., Kessler, R. C., & Takeuchi, D. National Comorbidity Survey Replication (NCS-R). In M. Alegria, J. S. Jackson, R. C. Kessler, & D. Takeuchi. Collaborative Psychiatric Epidemiology Surveys (CPES), 2001-2003 [UNITED STATES] [Computer file]. ICPSR20240-v5. Ann Arbor, MI: Institute for Social Research, Survey Research Center [producer], 2007. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2008-06-19.
- The suggested citation for the NCS-R is:
Jackson, J. S., Caldwell, C. H., Chatters, L. M., Neighbors, H. W., Nesse, R., Taylor, R. J., Trierweiler, S. J., & Williams, D R. National Survey of American Life (NSAL). In M. Alegria, J. S. Jackson, R. C. Kessler, & D. Takeuchi. Collaborative Psychiatric Epidemiology Surveys (CPES), 2001-2003 [UNITED STATES] [Computer file]. ICPSR20240-v5. Ann Arbor, MI: Institute for Social Research, Survey Research Center [producer], 2007. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2008-06-19. doi:10.3886/ICPSR20240.
- The suggested citation for the NSAL is:
Alegria, M., & Takeuchi, D. National Latino and Asian American Study (NLAAS). In M. Alegria, J. S. Jackson, R. C. Kessler, & D. Takeuchi. Collaborative Psychiatric Epidemiology Surveys (CPES), 2001-2003 [UNITED STATES] [Computer file]. ICPSR20240-v5. Ann Arbor, MI: Institute for Social Research, Survey Research Center [producer], 2007. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2008-06-19.
- The suggested citation for the NLAAS is:
Analysts who use Stata svy commands might get an error message "missing standard errors because of stratum with single sampling unit" and get no standard errors when Stata encounters a single PSU in a stratum. This situation happens when analysts extract either the Latino or Asian subpopulation from the whole NLAAS data set and only analyze the data based on either separated data set with Stata svy command.
The STATA error message arises because the full sampling error coding for NLAAS is joint for the Latino and Asian samples and several NLAAS sampling error strata include sampling error clusters that only contain Latino or Asian respondents. As a consequence, if the user conditionally restricts the input data for the analysis to only respondents from an NLAAS subpopulation, Stata detects a sampling error stratum in which all cases belong to a single sampling error cluster.
If you are conducting analysis that is restricted to subpopulations of respondents from the full NLAAS or CPES data sets, the following steps are recommended:
First of all, analysts may use the svydes command to show how respondents are distributed to sampling error strata and clusters. The Stata output will illustrate the NLAAS sampling error calculation model and the number of PSUs included in each stratum.
Theoretically, the preferred approach is to perform an unconditional subpopulation analysis based on the full NLAAS data set, which has both Latino and Asian subpopulations. To perform the analysis only for Latinos (or any other ancestry of demographic subpopulation of interest), first create an indicator variable that has a value of "1" for all eligible cases you wish to include in your analysis and a value of "0" for all other NLAAS cases. Then use the STATA subpop() option to restrict your analysis to the chosen subpopulation of cases. This approach results in correct estimates of the subpopulation statistics and the correct sampling error for these estimates. The "single PSU in a stratum" problem should be solved.
By example, to analyze NLAAS data for the Latino subpopulation, the subpop variable (e.g. latinos) should be equal to 1 for Latinos and 0 for Asians. Example syntax for the this analysis is:
svyset SECLUSTR [pweight= NLAASWG] , strata (SESTRAT)
svy, command subpop (latinos):
Although the unconditional approach to subpopulation analysis of the NLAAS/CPES data is the correct method, we recognize that many analysts may be working exclusively with either the NLAAS Asian or Latino data. The unconditional subpopulation analysis method described above requires the analyst to process all NLAAS cases even though statistical analyses are focused only on one of the major subpopulations. In this case analysts may employ and approximate method and use one of following Stata's ad hoc options, singleunit, for dealing with sampling error strata in which the subpopulation occurs in a single sampling error cluster:
- Singleunit (certainty): it means that the singleton PSUs be treated as certainty PSUs. Certainty PSUs are PSUs that were selected into the sample with a probability of 1 and do not contribute to the standard error.
- Singleunit (scaled): it gives a scaled version of the certainty option. The scaling factor comes from using the average of the variances from the strata with multiple sampling units for each stratum with one PSU.
- Singleunit (centered): it centers strata with one sampling unit at the grand mean instead of the stratum mean.
For analyzing the separate Latino data set, the syntax with singleunit (centered) command will be:
svyset SECLUSTR [pweight= NLSWTLA] , strata (SESTRAT) singleunit (centered)
- In FAQ #67 we discussed "How should I detect and handle the single PSU in a stratum for NLAAS or CPES Latino groups with Stata?" This FAQ is going to introduce how we should handle no subpopulation (Asian or Latino) members in a stratum for NLAAS Asian or Latino groups and perform an unconditional subpopulation analysis based on the full NLAAS data set.
Here we provide a case study along with two common questions/problems analysts usually need to deal with:Let's say we would like to test if there is a relationship between races/ancestries and gender for NLAAS Latino groups. The we can generate the cross-table of RANCEST and Sex variables and compute chi-square statistics for NLAAS Latino groups. However, there are no Latino groups in 12 strata so chi-square statistics will not be computed.
- Step 1: Create a copy of the race/ethnicity variable, and set values for the groups not in your subpopulation equal to one of the ethnicity values for groups in your subpopulation.
- Step 2: As FAQ #76 suggested, to perform the analysis only for Latinos (or any other ancestry of demographic subpopulation of interest), first create an indicator variable that has a value of "1" for all eligible cases you wish to include in your analysis and a value of "0" for all other NLAAS cases.
- Step 3: Use the STATA subpop() option to restrict your analysis to the chosen subpopulation of cases.
. svyset SECLUSTR [pweight=NLAASWGT], strata(SESTRAT)pweight: NLAASWGTVCE: linearizedSingle unit: missingStrata 1: SESTRATSU 1: SECLUSTRFPC 1: <zero>. generate RANCEST2 = 0. replace RANCEST2 = 5 if RANCEST<=5(2672 real changes made). replace RANCEST2 = 6if RANCEST==6(495 real changes made). replace RANCEST2 = 7if RANCEST==7(868 real changes made). replace RANCEST2 = 8if RANCEST==8(614 real changes made). generate LATINO = 0. replace LATINO = 1 if RANCEST>=5(2554 real changes made). svy, subpop (LATINO): tab RANCEST2 SEX(running tabulate on estimation sample)Number of strata = 57 Number of obs = 3956Number of PSUs = 114 Population size = 27942479Subpop. no. of obs = 2554Subpop. size = 21654900Design df = 57----------------------------------| SexRANCEST2 | MALE FEMALE Total----------+-----------------------5 | .0243 .0219 .04636 | .0489 .0516 .10057 | .3052 .2611 .56638 | .1366 .1503 .2869|Total | .515 .485 1----------------------------------Key: cell proportionsPearson:Uncorrected chi2(3) = 13.3482Design-based F(2.23, 126.94) = 4.3779 P = 0.0117Note: 12 strata omitted because they contain no subpopulation members.Below is the output of analyses if we skip the Step 1.You can see that the chi-square statistics was not computed because 12 strata contained no subpopulation (Latino) members.. svyset SECLUSTR [pweight=NLAASWGT], strata(SESTRAT)pweight: NLAASWGTVCE: linearizedSingle unit: missingStrata 1: SESTRATSU 1: SECLUSTRFPC 1: <zero>. generate LATINO = 0. replace LATINO = 1 if RANCEST>=5(2554 real changes made). svy, subpop (LATINO): tab RANCEST SEX(running tabulate on estimation sample)Number of strata = 57 Number of obs = 3956Number of PSUs = 114 Population size = 27942479Subpop. no. of obs = 2554Subpop. size = 21654900Design df = 57----------------------------------Race/Ance | Sexstry | MALE FEMALE Total----------+-----------------------VIETNAME | 0 0 0FILIPINO | 0 0 0CHINESE | 0 0 0ALL OTHE | 0 0 0CUBAN | .0243 .0219 .0463PUERTO R | .0489 .0516 .1005MEXICAN | .3052 .2611 .5663ALL OTHE | .1366 .1503 .2869|Total | .515 .485 1----------------------------------Key: cell proportionsTable contains a zero in the marginals.Statistics cannot be computed.Note: 12 strata omitted because they contain no subpopulation members.Below is the output if you conduct analyses on only NLAAS Latino groups with corresponding cluster, strata, and weight variables after dropping all Asian groups from the data set.You will see distributions among different race/ancestry and gender groups and chi-square statistics computed along using the Latino-specific weight variable (NLSWTLAT) are different from the case study we shown earlier. These differences are due to the fact that we used different weights in the two approaches. The overall NLAAS weight (NLAASWGT) adjusts the sample to a different population than the Latino-specific weight.We recommend that you should NEVER simply delete cases that are not in a particular subpopulation. After you create your indicator variable (see Step 2), you should always use the subpop() option rather than dropping cases or using if modifiers.. drop if NLSWTLAT==.(2095 observations deleted). svyset SECLUSTR [pweight=NLSWTLAT], strata(SESTRAT)pweight: NLSWTLATVCE: linearizedSingle unit: centeredStrata 1: SESTRATSU 1: SECLUSTRFPC 1: <zero>. svy: tab RANCEST SEX(running tabulate on estimation sample)Number of strata = 57 Number of obs = 2554Number of PSUs = 110 Population size = 21654900Design df = 53----------------------------------Race/Ance | Sexstry | MALE FEMALE Total----------+-----------------------CUBAN | .0238 .0224 .0463PUERTO R | .0517 .0487 .1005MEXICAN | .2917 .2746 .5663ALL OTHE | .1478 .1391 .2869|Total | .515 .485 1----------------------------------Key: cell proportionsPearson:Uncorrected chi2(3) = 0.0000Design-based F(2.30, 122.11) = 0.0000 P = 1.0000CPES Team
- Step 1: Create a new RANCEST2 variable, recoded all Asian groups? values (RANCEST=1, 2, 3, or 4) as the same as Cuban group (RANCEST=5).
- Step 2: Create an indicator variable LATINO hat has a value of "1" for all Latino groups a value of "0" for all other NLAAS cases.
- Step 3: Use the STATA subpop (LATINO) option with corresponding cluster, strata, and weight variables.
- There are three ways to browse the CPES codebooks interactively to view questions andsummary data (http:// or Figure 7).
- Interactive Codebook: This is one of seven navigational tabs available on the CPES Home Page (element 2 in Figure 1, The CPES Home Page) and at the top of all other CPES Web pages (Figure 8).
- Browse CPES by Subject: Available from the CPES Home Page, this allows users to browse sections of the CPES codebooks related to specific DSM-IV and ICD-10 diagnoses.
- Browse the Individual Surveys: Also available from the CPES Home Page, this allows users to browse the codebook for a selected individual CPES survey instrument.
- Go to the Diagnosis section of the National Comorbidity Web site and click on the NCS-R training PowerPoint where "Diagnostic Algorithms for the NCS-R/DSM-IV-TR Disorders" are mentioned. There is a slide explaining how organic exclusions were handled as well as a wealth of information on the diagnostic algorithms and hierarchy rules used.
- The core questionnaire was based largely on the World Health Organization's (WHO) expanded version of the Composite International Diagnostic Interview (CIDI) developed for the World Mental Health (WMH) Survey Initiative, the WMH-CIDI.
For more information, consult the Questionnaire Development section of About CPES, or view a 22-minute video of Ron Kessler speaking on the development of CIDI.
- The vast majority of all the interviews were administered by lay interviewers using computer-assisted personal (face-to-face) interviews (CAPI). All interviews started as CAPI interviews. Some interviews were administered by phone if an interviewer was not available locally who spoke the respondent's preferred language or if the respondent preferred to be interviewed over the phone. Some interviews were also very long and had to be completed in more than one session, with later sessions more likely to be conducted over the phone. For more detailed information, please see the Survey Management section or Data Collection section of About CPES.
- Yes, some questions and created measures were dropped after the Disclosure Committee completed their analyses in order to safeguard respondent anonymity. However, there is a restricted-use data set that contains some of these questions and measures that were considered sensitive. You can apply to receive a copy of the data set by following ICPSR's instructions on restricted-use data.
Please refer to the Data Processing Notes for the transformations that were made to the files as well as the variables that were dropped from the files for disclosure reasons.
- Our evaluation of the NCS-R NAP variable shows that it is not sufficiently robust to be used in analysis. That is why we did not release it in the public-use data file. We are unable to make it available to you for the same reason. We are sorry, but are concerned that the variable could do more harm than good.
- There are two versions of the CPES data sets: a public-use version that is available to everyone and has no identifiable data and a restricted-use version that contains more sensitive information but still not any direct identifiers. Researchers must request the restricted-use version through the Applying for Restricted-Use Data process that includes signing an Agreement and providing a data protection plan.
- It is up to your Institutional Review Board to decide whether or not they will review your proposal. As Clause 20 of the Agreement states: If the Receiving Organization requires a review of research proposals using secondary survey data by an Institutional Review Board/Human Subjects Review Committee or equivalent body, that review has taken place and all approvals have been granted prior to application for use of the restricted data.These data do not have direct identifiers but the additional variables provided in the restricted-use file do contain sensitive information about each respondent which may potentially increase the chance that one might be identified.
- There is no FPC variable created in the data set for public-use. A person who wants to incorporate a finite population correction could do so by creating his own FPC variable. In general, analysis of the CPES does not use a correction for FPC as it amounts to a very small correction in the end, due to large sample sizes to begin with.
- With some of our data files, McAfee Antivirus returns false virus warnings, which are caused by a conflict in the McAfee VirusScan engine before Version 4.5.1. Network Associates, who now own McAfee, have seen this problem and recommend that upgrading to their 4.5.1 engine resolves it. We have done a few tests and it seems to be true across different versions of Windows.Please note that this refers to updating the virus engine. Updating your virus definitions file will not resolve this conflict.Most files that we distribute are plain character files--mostly ASCII but some EBCDIC. Unless tampered with after leaving our site, they cannot in principle contain a virus. Any suggestion of viruses in our distribution archive is taken very seriously, but at least for the character data, it is very unlikely that they are real.If you are currently using the McAfee VirusScan pre-4.5.1, we strongly recommend you upgrade. If you find a virus warning with Version 4.5.1 or later, or with different virus scanning software, please report the problem to email@example.com immediately. If you need to report a virus, please be sure to include the study number and the file name in your email message.
- ICPSR and Survey Research Operations of the Institute for Social Research, University of Michigan, are pleased to announce the release of the Collaborative Psychiatric Epidemiology Surveys (CPES), which provide data on the distributions, correlates, and risk factors of mental disorders among the general population, with special emphasis on minority groups. Funded by the National Institute of Mental Heath, this project joins together three nationally representative surveys: the National Comorbidity Survey Replication (NCS-R), the National Survey of American Life (NSAL), and the National Latino and Asian American Study (NLAAS).
The CPES Web site provides a number of ways to explore the CPES data:
- Use the Interactive Documentation to compare questions and variables across the merged CPES file and the three separate files
- Download the data in ASCII, SPSS portable, SAS transport, or Stata system format along with the documentation for desktop analysis
- Investigate and visualize the CPES data through the SDA online analysis system, which enables a variety of analytic tasks
- Search on specific variables or topics of interest
- Browse the CPES data by DSM-IV or ICD-10 diagnostic headings
- Dear CPES users:
The new Collaborative Psychiatric Epidemiology Surveys (CPES) Web site if available for the public now! For more detailed information, please refer to the updated Web Site User's Guide!
- Key tabs or navigational links:
- Additional links for:
- Options (in addition to the Interactive Codebook tab) for comparing questions and variables across CPES and the individual surveys:
- New restricted files for the studies comprising CPES (NCS-R, NSAL, NLAAS) and are now available in SAS, SPSS and STATA.
These files contain more variables than released with the previous version of the restricted files in May, 2008.
Please note that we have not harmonized these data but have provided tables for each file that list the names of all variables along with their labels and formats.
- NCSR Restricted Dataset (Excel 75K)
- NSAL Restricted Dataset (Excel 52K)
- NLAAS Restricted Dataset (Excel 66K)
- CPES Restricted Crosswalk (Excel 109K)
Analysts wanting to request the restricted files should consult ICPSR's instructions on Applying for Restricted Data and complete the forms as outlined. Analysts wishing geographic identifiers should contact firstname.lastname@example.org. Distributions for restricted data can be viewed in the Interactive Codebook tab on the CPES Web site.
- Users who downloaded the earlier standalone version of NCS-R (ICPSR 4438) will note that updated NCS-R data are now being distributed as part of the larger CPES project. Those using NCS-R only can find NCS-R specific PDF documentation that was formerly distributed with ICPSR 4438, along with the NCS-R data packaged for online analysis.
In addition, NCS-R interactive documentation is now available on the CPES site and NCS-R data are downloadable separately as Dataset 2, National Comorbidity Survey Replication (NCS-R), 2001-2003.
- The master CPES datasets are updated periodically as various, typically small, errors are detected. Diagnostic algorithms are periodically updated as well. This updating will continue in the future as needed and public users will be informed of these updates. It is important for public users to recognize that, because of these changes, it will not always be possible to reproduce results reported in earlier publications.
- An additional component of the National Survey of American Life, 2001-2003 (NSAL) is now available but only as a restricted file (ICPSR Study Number 27121). Analysts wanting to request this file should consult ICPSR's instructions on Applying for Restricted Data and complete the forms as outlined.
Here is a short summary of the contents of this dataset:
The National Survey of American Life, 2001-2003 (NSAL) was followed up by a self-administered interview (NSAL SAQ) as a way to reduce respondent burden following the 2 1/2 hour NSAL survey. The SAQ includes additional questions about social, group, and individual characteristics: psychological resources (i.e., John Henryism), group and personal identity (racial awareness and identity), as well as ideology and racial relations (i.e., social dominance; stratification beliefs; egalitarianism; national pride; work ethic; authoritarian, interracial contact; and exposure to Black social contexts); political attitudes (i.e., Race-conscious Policy Index, Race-blind Policy Index, Non-Electoral Participation Index); care of elderly values; job and financial stressors; and wealth. Demographic variables include age, race, and sex.
For more information, visit the ICPSR Web site.
- Restricted files for the studies comprising CPES (NCSR, NSAL, NLAAS) and are now available in SAS, SPSS and STATA. Please note that we have not harmonized these data but have provided a table (Excel 91K; PDF 82K) that compares questions across studies so analysts can consult these before merging and harmonizing these data. These data also have not been cleaned to the same standards as those data in the public release files. Analysts wanting to request the restricted files should consult ICPSR's instructions on Applying for Restricted Data and complete the forms as outlined. Analysts wishing geographic identifiers should contact email@example.com. Distributions for restricted data can be viewed in the Interactive Codebook tab on the CPES Web site.
- The two variables needed to correctly estimate sampling error (SESTRAT and SECLUSTR) were inadvertently left off the individual data files for each of the three CPES studies. Until these are added back in, users can simply download the merged CPES file (where these variables are present) and then subset the file. For users who want only NCS-R, the file can be subset using the project identification variable CPESPROJ = 1; for users only wanting NLAAS, use CPESPROJ = 2; for users wanting NSAL, use CPESPROJ = 3. Please also refer to section VII. Sampling Error Computation Models in the Users Guide for additional information.
- Yes, it must receive approval or exemption from the Institutional Review Board.
- For a few select studies, the total file size for the compressed download can come close to 20GB, which is more than most Web browsers can handle. There are two options for successfully downloading the study:
- Download a single data set at a time.
- Use Opera to download the study. We don't wish to advocate one Web browser over any other, but Opera can handle larger downloads that Internet Explorer, Mozilla, FireFox, Netscape Navigator/Communicator, and Safari cannot.
- Obsessive Compulsive Disorder was not assessed in NLAAS. NSAL assessed it using the DSM-IV Short form module and the questions for this module can be found in variables O1-O17B1.
For NCS-R, there was a problem with the skip logic for OCD which caused the disorder to be underestimated in the CIDI. Therefore NCS-R is no longer using this disorder in their papers and did not release the data.
- Item SC10.4b reads "Do you have the following conditions? A hearing problem that prevents you from hearing what is said in normal conversation even with a hearing aid?" This item appears to be asked of all respondents.Further down, there are 2 interviewer query items dealing with hearing loss -If the respondent says no to the hearing question (or other impairment questions) but the interviewer observes a hearing problem (or other impairment), this is an opportunity to probe with the respondent to be sure she or he had understood the original question. This is repeated for several of the ?observable? impairments when there appears to be a discrepancy between what the respondent said and what the interviewer observes.
- Dear CPES Data User:
Our records indicate that you have downloaded data from the Collaborative Psychiatric Epidemiology Surveys (CPES) Web site. We want to let you know that revised and corrected CPES data are now available, and older version should no longer be used.
Over the past six months, the staffs of the three projects that comprise CPES have continued to work with these data, cleaning discrepancies, updating algorithms, and identifying additional variables that can be harmonized. They have created new versions of the CPES files that contain thousands of these types of changes, many at the cell level. Many of these changes represent errors in the original data; therefore previous versions of the CPES file are obsolete and should not be used. The data producers were careful not to change any variable names so that you can use previously-developed code to run against these corrected and updated files to determine if any of these changes impact your analysis.
We want to especially alert previous users of NCS-R. Here, numerous wording errors and problems with how missing data were handled in the original NCS-R releases were identified and corrected. Again, the version of NCS-R in the newest release of CPES (released today) should be used instead of any previous NCS-R releases.
We apologize for the inconvenience this may cause. Please contact ICPSR User Support at firstname.lastname@example.org if you have any questions or concerns.
Please see the CPES Data Processing Notes for updated lists of recoded and dropped variables.
ICPSR User Support
- When scrolling through all variables in a section of an NCS-R, NLAAS, or NSAL instrument via the Browse the Individual Surveys link on the CPES Home Page, there is additional information available for some questions. In addition to question text and response options, there may also be links to respondent booklet information provided to respondents to assist in choosing response options, and interviewer instructions (generally question-level objectives or definitions).If available these follow the question text and response options under the header Additional Documentation (see Figures 24 and 25). Clicking on a link for additional information opens a new window. Click on the browser Back button to return to the question window.Figure 24. Additional Question Documentation: Respondent BookFigure 25. Additional Question Documentation: Interviewer Instructions
- From the CPES Home Page, users may view Diagnostic Variables, by a disorder category, for example, Mood, under either DSM-IV (Diagnostic and Statistical Manual of Mental Disorders, 4th Edition) or ICD-10 (International Classification of Diseases, 10th Revision). They may also click on either DSM-IV or ICD-10 to see a list of disorders under either classification.For example (Figure 31), clicking on Mood under DSM-IV, and then clicking on Bipolar, brings up a list of constructed variables for DSM-IV Bipolar Mood Disorder, documentation on how they were constructed (see Diagnostic Documentation), and variables in the relevant sections (Depression and Mania).Note that there are not always parallel ICD-10 constructed diagnostics for all DSM-IV diagnostics. For example, there are no ICD-10 Bipolar, Major Depressive Disorder, or Major Depressive Episode diagnostic variables.Figure 31. Browsing by Subject: DSM-IV Bipolar Mood Disorder
- Users may go directly to the interactive documentation for an individual survey (NCS-R, NLAAS, or NSAL) from the CPES Home Page, by clicking on the survey name. Functionality is the same as with Interactive Documentation, except that the focus is initially on the survey tab (e.g., NLAAS, as shown in Figure 32) rather than the CPES tab. Links to Web sites for the individual studies are also available on the CPES Home Page, in the upper left corner under Using CPES (see also Related Links).Figure 32: Browsing Interactive Documentation for NLAAS
- Documentation for constructed diagnostic variables is available for each diagnostic variable section, for example DX Bipolar (Figure 30). Click on the DSM-IV Bipolar link to open a PDF document with information on the construction of the bipolar diagnostic variables. Click on the browser back button to return to the DX Bipolar list of variables. See also Browse CPES by Subject.Figure 30. Documentation for The Diagnostic Variables in The DX Bipolar Section
- The CPES dataset has 27 sections with constructed diagnostic variables. Each begins with the letters ?DX? (Figure 28), and contains constructed 30-day, 12-month, and lifetime diagnoses, as well as onset and recency, and in some cases subthreshold measures.Figure 28. CPES Sections for 27 DiagnosesFigure 29 shows a variable in the DX Bipolar section. Note that the linked variables for individual studies appear in a different section (?Supplemental?) in their interactive documentation.Users may also view CPES DX Bipolar variables via the CPES Home Page, by clicking on the Mood link under Browse CPES by Subject .Figure 29. CPES Diagnostic Variable V07555 and Linked NSAL Variable D_BIPOLAR12
- Processors dropped many variables in the NCS-R, NLAAS, and NSAL source datasets, for the following reasons:
- To protect the identity of research subjects, including dropping source variables for constructed demographics created to mask identity;
- If they were source variables for constructed variables created for other purposes (e.g., NSAL?s variable E14a-e15a, which has combined data from three questions that resulted from routing respondents through three different question wordings to gather the same data); or
- If they were the following types of computer-assisted instrument variables:
Figure 27 shows a variable dropped from the NCS-R Post-Traumatic Stress Disorder section.Click on view the summary statistics and/or frequencies link to view the frequencies for this question to see how many respondents answered ?Yes.? See the ?Dropped Variables? section of the Data Processing Notes for a list of variables that fall into categories 1 and 2 above and that were removed from the individual survey datasets.Figure 27. An NCS-R Variable Dropped from the Post-Traumatic Stress Disorder Section
- Open-ended question with text response;
- Open-ended ?other specify? question with text response;
- Instrument screen with introductory text (?ENTER 1 TO CONTINUE?);
- Interviewer checkpoint or instruction screen; or
- Interviewing software routing check.
- The NLAAS survey was conducted in five languages: English, Spanish, Vietnamese, Tagalog,and Chinese. When viewing an NLAAS variable (Figure 16; see Variables), the primary tab(Total) will show the total frequency distribution or summary statistics for all respondents. Clickon any of the five language tabs to view variable information for respondents interviewed in thatlanguage. Figure 16 shows frequencies on NLAAS variable SC35?for all interviewed inChinese.Figure 16. Frequencies for Variable SC35: All Respondents (Total) and Chinese Respondents
- CPES has linked variables from the individual studies in which there were minor wordingchanges (that is, not believed to substantially change meaning). These are highlighted invariables lists with red asterisks ( * ). Click on such a variable (e.g., NSAL M3A*), and then clickon the compare question text link to view the differences (Figure 14).Figure 14. Compare Question Text Link: Viewing Minor Wording Changes Across Linked QuestionsNote that questions are not linked if changes could possibly alter question interpretation. Forexample, the Screening variable SC35 appears as two separate CPES variables, one for theNCS-R question that did not include the words ?as an adult?, and one for linked NLAAS andNSAL questions that did (see Figure 15).Figure 15. Question Wording Differences across Unlinked Screening Questions (SC35)
- Every attempt was made to harmonize variables across study datasets, including linkingvariables that appeared in different sections across the three studies. A red dagger ( ? )appears next to such variables, indicating that they came from sections other than the currentsection. For example (Figure 17), when looking at the list for CPES variables in the Financesection, V05315 shows NLAAS variable FN13A and NSAL variable H47. H47 has a red daggernext to it. This indicates that it is not in the Finances section of the NSAL instrument. It actuallyappears in the Personal Data section. CPES always shows at the top of the screen theinstrument and section for the currently selected variable; for example:
In these examples, you may click on the CPES or NSAL links to go to its sections list, or on thesection links to go directly to the CPES Finances section or the NSAL Personal Data section.Figure 17. CPES Finance Section Variables That Appear in Two Different Source Instrument Sections
- file: CPES > section: Finances > language: English, or
- file: NSAL > section: Personal Data > language: English.
- When scrolling through all variables in a section of the NCS-R, NLAAS, or NSAL instrument, the survey population to which a question applies, that is, the universe, is noted for each question. If all respondents were asked the question, the notation will be ?Applies to all respondents.? If not, there will be a View Universe link. Clicking on the link will expand the universe, indicating the prior responses that controlled whether the respondent was asked the displayed question. The example in Figure 26 shows that the universe for NCS-R variable AG4e (CPES variable V01650) is all respondents for which the value of AG2 is 1.Clicking on the AG2 link in the expanded universe shows that AG2 is an interviewer query about how many ?Yes? responses the respondent gave in the AG1 question series, and that if a respondent gave less than two ?Yes? responses in this series, question AG4e applied to that respondent. Interviewers did not ask AG4e of other respondents. AG1 is not in the CPES dataset.Figure 26. The Universe for NCS-R Question AG4e:Respondents Who Gave Less Than Two ?Yes? Responses to AG1a through AG1kNote that universes are derived from the computer assisted survey instrument flow logic and represent one or more conditions under which the question would be asked of a respondent. If there are two or more conditions, each is listed on a separate line, with an implicit logical AND operator between conditions. For example, for the NLAAS variable FD7B (CPES variable V04461):FD6 = 2(FD7_1 = 3) OR (FD7 = DONTKNOW)Thus, the correct interpretation of these conditions is:FD6 = 2 AND((FD7_1 = 3) OR (FD7 = DONTKNOW))This means:Respondents who answered NLAAS question FD7B first answered (1) ?2? to SR1701, and (2) either ?3? to FD7_1 or ?Don?t Know? to FD7.
- Click on a section name to view a list of CPES variables in that section (Figure 11). CPESnumeric variable names begin with ?V? and are listed on the left. Linked NCS-R, NLAAS, andNSAL variables are displayed on the right. Note that since some sections and variables areunique to studies, there will not always be linked variables for all three studies (see InstrumentSections).Figure 11. Variables List for CPES Section Agoraphobia.Click on any variable name to go to a page with two to four tabs, one for the CPES variable, andup to three linked study variables (Figure 12). The variable selected determines which tab isactive. For example, clicking on CPES V01627 makes the CPES question tab active, andclicking on AG1B on the same line makes the NCS-R tab active.Each tab displays question text and applicable response options, as well as frequencydistributions (Figure 12) or summary statistics (Figure 13). The CPES tab has statistics for the20,013 cases in the merged dataset, and each study tab shows comparable statistics for theselected individual study. Click on tabs to move back and forth among the CPES and studyspecific variables.Each individual study tab shows the universe of respondents who were asked the question (seeUniverses). The CPES documentation does not show universes, since they vary acrossindividual instruments.On each variable page, there also are links at the top and bottom to allow you to move to theprevious and next question in the section.Figure 12. CPES Variable V01627 and NCS-R Variable AG18: Combined and Study-Specific Frequency DistributionsFigure 13. CPES Variable V01640 and NLAAS Variable AG3A: Combined and Study-Specific Summary Statistics
CPES Interactive Documentation shows you information at the variable label. To scroll through a complete section, click on the view all variables in this section at the top or bottom of the section contents page (Figure 21), or on scroll through all the questions in this section at the bottom of the variable information page (Figure 22).
Figure 21. Links for Viewing All Variables in Section (Contents Page)
To view all questions from a single question (Figure 22), click on the scroll through all the questions in this section link at the bottom of the page. To view all questions in a separate window, click on the window icon (http://).
Figure 22. Links for Scrolling Through All Variables in A Section (Single Question Page)
To return to the section contents or the single question page scrolling section page, click the browser Back button (or the browser window close button if you opened the scrolling page in a separate window).
Note that if you click on a variable tab when scrolling through a section, Interactive Documentation will take you to a page with that one variable (Figure 23). Click on the browser Back button to return to the scrolling view.
Figure 23. Scrolling Section and Single Question Views
- The CPES Interactive Documentation allows users to view a CPES variable in SDA, the ICPSRonline analysis system (developed by the University of California-Berkeley), which hasadditional information about the variable.On any variable screen (Figure 18) click on view this variable in SDA to view the variable inSDA format. If you click on the window icon ( http://), a separate window will open. OnlineAnalysis using SDA also is available for all four CPES datasets (CPES, NCS-R, NLAAS, andNSAL).The first time in a CPES Web session that a user tries to access SDA, Download Data, or doOnline Analysis, user authentication is required, that is, a user must enter an email address andpassword for an ICPSR ?MyData? Account (see ICPSR ?MyData? Account Options).Figure 18. Options for Viewing a CPES Variable in SDA, the ICPSR Online Analysis SystemFigures 19 and Figure 20 show what information SDA provides for a question with responseoptions (V01627) and a numeric question (V01640). Unlike the CPES InteractiveDocumentation, SDA gives the frequency distribution for responses to numeric questions(Figure 19). Note also that missing data codes are 7, 8, and 9 [Missing (Other) Don?t Know,Refused] in the Interactive Documentation, and -7, -8, -9 in SDA. See the ?Missing Data Codes?section of the Data Processing Notes for further information on the ?Missing (Other)? codes.Figure 19. SDA View for CPES Variable V01627 (Enumerated Response OptionsFigure 20. SDA View for CPES Variable V01640 (Numeric)To return to the CPES variable in Interactive Documentation, click on the browser Back button(or the browser window close button if you opened a separate SDA window).
- As part of the WHO Composite International Diagnostic Interview (CIDI 3.0) training program, Ronald Kessler, Professor of Health Care Policy at Harvard Medical School and Chair of the CIDI Advisory Committee, provided the background and history of the development of the CIDI, the instrument that was used to collect the diagnostic data in the CPES. You may view a 22-minute video of his presentation.
- Three videos and corresponding PowerPoint slides are now available from the 2008 CPES Training Workshop. For optimal viewing (1) select a .MOV file by right-clicking on the hyperlink and choosing "saving target as." Save the file in your chosen location and launch it in QuickTime Player. This will allow the image to be re-sized. (2) Otherwise, left-click on a .MOV or .MPG file and the file will automatically launch in your browser window. Please note that the files may take a few minutes to load. The videos incorporate the PowerPoint slides. The slides are also provided as stand-alone documents.
- Steve Heeringa: Sample Design and Weighting (PPT 778K)
- Pat Berglund: Analysis of Complex Sample Survey Data (MOV 342MB; MPG 482MB; PPT 599K)
- Myriam Torres: Examples of Complex Design-Corrected Analyses Using CPES (MOV 189MB; MPG 277MB; PPT 61K)
- Steve Heeringa: Sample Design and Weighting (PPT 778K)
- We inadvertently did not ask D23 of the CIDI, the question that operationalized bereavement, in the CPES. As a result we were unable to operationalize the bereavement criterion.
- Yes, all three studies were approved by the University of Michigan Institutional Review Board (IRB) before they went into the field.
Many of our data collections that contain ASCII data files are accompanied by setup files that allow users to read the text files into statistical software packages. Since a visual interpretation of alphanumeric data files is inefficient, statistical software is needed to define, manipulate, extract, and analyze variables and cases within data files. We currently provide for many of our data collections setup files for SAS, SPSS, and Stata statistical software packages, three of the more commonly used analytical software packages for the social sciences.
The following instructions explain the different components of SAS, SPSS, and Stata setup files. Setup files for certain collections may not contain all of the commands listed below.
SAS Setup Files
SAS setup files can be used to generate native SAS file formats such as SAS datasets, SAS xport libraries, and transport files. Our SAS setup files generally include the following SAS sections. Click on each section to see an example taken from ICPSR 6512 (Capital Punishment in the United States, 1973-1993).
- PROC FORMAT: Creates user-defined formats for the variables. Formats replace original value codes with value code descriptions. Not all variables necessarily have user-defined formats.
- DATA: Begins a SAS data step and names an output SAS dataset.
- INFILE: Identifies the input data file to be read with the input statement. Users must replace the "physical-filename" with host computer-specific input file specifications. For example, users on Windows platforms should replace "physical-filename" with "C:\06512-0001-Data.txt" for the data file named "06512-0001-Data.txt" located on the root directory "C:\".
- INPUT: Assigns the name, type, decimal specification (if any), and specifies the beginning and ending column locations for each variable in the data file.
- LABEL: Assigns descriptive labels to all variables. Variable labels and variable names may be identical for some variables.
- FORMAT: Associates the formats created by the PROC FORMAT step with the variables named in the INPUT statement.
- MISSING VALUE RECODES: Sets user-defined numeric missing values to missing as interpreted by the SAS system. Only variables with user-defined missing values are included in the statements.
SPSS Setup Files
SPSS setup files can be used to generate native SPSS file formats such as SPSS system files and SPSS portable files. SPSS setup files produced by
generally include the following SPSS sections. Click on each section to see an example taken from ICPSR 6512 (Capital Punishment in the United States, 1973-1993).
- DATA LIST: Assigns the name, type, decimal specification (if any), and specifies the beginning and ending column locations for each variable in the data file. Users must replace the "physical-filename" with host computer-specific input file specifications. For example, users on Windows platforms should replace "physical-filename" with "C:\06512-0001-Data.txt" for the data file named "06512-0001-Data.txt" located on the root directory "C:\".
- VARIABLE LABELS: Assigns descriptive labels to all variables. Variable labels and variable names may be identical for some variables.
- VALUE LABELS: Assigns descriptive labels to codes in the data file. Not all variables necessarily have assigned value labels.
- MISSING VALUES: Declares user-defined missing values. Not all variables in the data file necessarily have user-defined missing values. These values can be treated specially in data transformations, statistical calculations, and case selection.
- MISSING VALUE RECODE: Sets user-defined numeric missing values to missing as interpreted by the SPSS system. Only variables with user-defined missing values are included in the statements.
Stata Setup Files
Stata setup files can be used to generate native Stata DTA files. Stata setup files produced by ICPSR generally include the following Stata sections. Click on each section to see an example taken from ICPSR 6512 (Capital Punishment in the United States, 1973-1993).
- FILE SPECIFICATIONS: Assigns values to local macros that specify the locations of the files used to build a Stata system file. Users must replace the "physical-filename" with host computer-specific input file specifications. For example; users on Windows platforms should replace "raw-datafile-name" with "C:\06512-0001-Data.txt" for the data file named "06512-0001-Data.txt" located on the root directory of "C:\". Simarlarly, the "dictionary-filename" should be replaced with "C:\06512-0001-Stata_dictionary.dct". The "stata-datafile" specification should be named with the specification for where you wish to store the Stata system file.
- INFILE COMMAND: Reads the columnar ASCII data into a Stata system file.
- VALUE LABEL DEFINITIONS: Defines descriptive labels for the individual values of each variable.
- MISSING VALUES: Replaces numeric missing values (i.e., -9) with generic system missing ".". By default the code in this section is commented out. Users wishing to apply the generic missing values should remove the comment at the beginning and end of this section. Note that Stata allows you to specify up to 27 unique missing value codes.
- SAVE OUTFILE: This section saves out a Stata system format file. There is no reason to modify it if the macros in Section 1 were specified correctly.
- This describes the main scales we used in the NCS-R and then again in the NCS-A:The questions in the Personality sections include items from the social desirability scale of the Zuckerman Personality Scales and a subset of the screening questions from the screening scale developed in conjunction with the International Personality Disorder Examination (IPDE). The Zuckerman items were included to facilitate the study of social desirability response bias in the survey.The IPDE screening questions were included as a screening scale for a small clinical reappraisal study of personality disorders that was carried out in a probability sub-sample of NCS-R respondents. This reappraisal study administered the full IPDE. The method of multiple imputation (MI) was used to generate predicted probabilities of DSM-IV diagnoses of Clusters A, B, C, and any PDs (including NOS) as well as diagnoses of antisocial personality disorder and borderline personality disorder. The latter two were the only specific personality disorders included in the MI analysis due to the fact that we had a special interest in them and we included the full set of IPDE screening questions for those two but only a subset of screening questions for other personality disorders.A paper reporting the results of the analysis was written by Mark Lenzenweger et al: Lenzenweger, M.F., Lane, M.C., Loranger, A.W., Kessler, R.C. (2007). DSM-IV personality disorders in the National Comorbidity Survey Replication. Biological Psychiatry 62(6), 553-564.
- Zuckerman Personality Scales:
- Zuckerman M, Psychology of Personality (Cambridge University Press: Cambridge, 1991); Zuckerman M, Behavioral expressions and biosocial bases of personality (Cambridge University Press: New York, 1994);
- Zuckerman M, Link K, Construct validity for the sensation-seeking scale, J Consult Clin Psychol (1968), 32:420-6;
- Zuckerman M, Bone RN, Mangelsdorff D, Brustman B, What is the sensation seeker? Personality trait and experience correlates of the sensation-seeking scales, J Consult Clin Psychol (1972), 39:308-21;
- Zuckerman M, Eysenck S, Eysenck HJ, Sensation seeking in England and America: Cross-cultural, age, and sex comparisons, J Consult Clin Psychol (1978), 46:139-49; Zuckerman M, Kuhlman DM, Personality and risk-taking: Common biosocial factors, J Pers (2000), 68:999-1029.
- ZuckermanM, KuhlmanDM, Joireman J,Teta P,KraftM. A comparison of the three structuralmodels for personality: the big three, the big five, and the alternative five. J Pers Soc Psychol. 1993;65.
- International Personality Disorder Examination (IPDE):
We did, however also use some other scales in NCS-A, which include:
- Loranger AW, Sartorious N, Andreoli A, Berger P, Buchheim P, Channabasavanna SM, Coid B, Dahl A, Diekstra RFW, Fergusin B, Jacobsberg LB, Mombour W, Pull C, Ono Y, Reiger D, The International Personality Disorder Examination (IPDE): The World Health Organization/Alcohol, Drug Abuse, and Mental Health Administration International Pilot Study of Personality Disorders. Arch Gen Psychiatry (1994) 51:215-24.
- Loranger AW, Sartorius N, Janca A, Assessment and Diagnosis of Personality Disorders: The International Personality Disorder Examination (IPDE) (Cambridge University Press: New York, 1996).
- PEB - World Assumptions scale - Janoff- Bulman, R (1989) Assumptive Worlds and the Stress of Traumatic Events: Applications of the Scema Construct. Social Cogintion: 7(2); 113-136.
- PEB - Self esteem scales - Rosenberg Self esteem scale - 81. Rosenberg AA, Kagan J. Physical and physiological correlates of behavioral inhibition. Dev Psychobiol. 1989;22; 753-770
- PEB - Locus of control - Levenson H. Multidimensional locus of control in psychiatric patients. J Consult Clin Psychol. 1973;41:397-404.
- Both DSM and ICD criteria were used to create the diagnostic measures. You can view a list of PDF documents that explain in detail how the DSM-IV/ICD diagnostic variables were created.
You can find a description of the criteria used for each diagnosis on the NCS-R Web site. Proceed to the NCS-R diagnostic documents that describe the algorithms used for the diagnostic variables. From there you will need to drill down to the correct NCS-R diagnostic zip file with diagnostic variable descriptions.
- Some disorders have hierarchy rules. They mean something different for each disorder. Go to the Diagnosis section of the National Comorbidity Web site and click on the NCS-R training PowerPoint where "Diagnostic Algorithms for the NCS-R/DSM-IV-TR Disorders" are mentioned. One of the slides lists the disorders that apply hierarchy rules and gives examples of what they mean. Information on the hierarchy rules is also available in the DSM IV Training Manual.
- CPES stands for the Collaborative Psychiatric Epidemiology Surveys, which were funded by the National Institute of Mental Health (NIMH). The CPES joins three nationally representative surveys and there are 20,013 cases in the CPES:
- The CPES dataset uses the following missing data codes:
- -7 Missing (Other)
- -8 Don't Know
- -9 Refused
- The ?Valid %? includes the cases that had responses without ?Don?t Know? or ?Refusal? for that question; the ?Total %? counts all of the cases in the study.
- An ASCII file is a plain text file consisting of numbers, letters, and symbols with no formatting. An ASCII file can be opened in any word processing program. It can only be analyzed, however, if it is read into a database, statistical, or spreadsheet software package. Data definition statements are necessary to read fixed-format ASCII files. See How to Interpret a Record from an ASCII Data File for more information.Software-specific files, such as SPSS portable files, SAS transport files, Excel spreadsheets, or Microsoft Word documents, are configured for use with their respective software packages. These files may be used with software other than that in which they were created, if the desired software allows the conversion. Users should keep in mind that some changes, especially regarding formatting, might occur in the translation.
- Major Depressive Disorder is a clinical course characterized by one or more major depressive episodes without the presence of manic/mixed or hypomanic episodes. For study purposes, a diagnosis of major depressive disorder without hierarchy (variable name=MDD) was created which differs from DSM in that whether manic/mixed or hypomanic episodes are or have been present is not part of the diagnosis; in other words, mania exclusionary criteria are not applied. In contrast, a diagnosis of major depressive disorder with hierarchy (variable name=MDDH) is identical to a DSM major depressive disorder diagnosis.
- You may do this by choosing a variable that only respondents who answered Part 2 completed and then do a cross tabulation by the variable ?sex?. For example, all 5,692 participants answered Question DA39 (Is biological mother still living?). When this variable is cross tabulated with the variable ?sex?, the distribution is 2,382 males and 3,310 females (unweighted). You may want to try other variables from the long form in similar crosstabs to check the gender breakdown.
- Since NCS-R was administered in two parts. Part 1 included a core diagnostic assessment of all 9,282 respondents. Part 2 included questions about risk factors, consequences, other correlates, and additional disorders. Part 2 was administered only to 5,692 of the 9,282 Part 1 respondents. Values for the NCS-R GROUP variable are: 1= Long Group, 2=Intermediate Group, 3= Short Group.
The CPES represents the English-speaking non-Hispanic White, African American, and Caribbean Black populations; the English- and Spanish-speaking Mexican, Puerto Rican, and Cuban populations; and the English-, Tagalog-, Vietnamese-, and Chinese-speaking Chinese, Filipino, and Vietnamese populations of the United States. Individuals of "other" race/ethnic background and "other" Latino and Asian ancestry were also included, but U.S. population representation of these groups was not possible.
In making our population projections, we have used a population estimate of 209,128,094 million people. This is the number of people ages 18+ in the US in 2001 based on published Census data. The majority of all respondents were interviewed in 2001 and therefore this is the best population we can use for our projections. We did not pull out homeless or institutionalized people or people who don't speak English, all of whom were excluded from our sample. These people probably make up about 5% of the population. We don't want to reify our rough estimate of population size, though, so you should feel free to use another estimate. For example, you might want to average the Census population estimates over the years of the survey and/or adjust for the exclusion of the non-household population.
- The proportion of non-disorder questions varies for each study. Most of these consist of risk and protective factors such as physical health, neighborhood conditions, religion, social support, psychological and other resources, and so on. There is some overlap in these items, but each study has its own unique set of questions. See the section list for an understanding of the non-disorder content.
- Looking through Questionnaire sections and average time to administer section by study table in the Questionnaire Development section of About CPES, it is possible to determine which sections were included in more than one study.
- Although the Screening section was a core section, only questions SC20 to SC36 were used in all three studies.
- In the Personality section, only a subset of 10 Personality questions were considered core. The service use questions at the end of each core section also varied by study.
- There are also questions interspersed throughout the three study instruments that were included in two or all three studies.
Table 1. Questionnaire Sections and Average Time to Administer Section by Study
NCS-R Time NSAL Time NLAAS Time 1. Household Listing 5:12 0. Household Listing 4:41 1. Household Listing n/a 2. Screening 16:55 8. Screening 9:21 3. Screening 18:52 3. Depression 8:04 9. Depression 6:45 4. Depression 10:20 4. Mania 5:52 10. Mania 4:58 - - 5. Irritable Depression 2:43 - - 5. Irritable Depression 5:41 6. Panic (PD) 4:55 11. Panic (PD) 4:51 6. Panic (PD) 5:08 7. Specific Phobia 7:13 - - - - 8. Social Phobia 7:45 12. Social Phobia 8:42 7. Social Phobia 9:32 9. Agoraphobia 6:46 13. Agoraphobia 7:11 8. Agoraphobia 8:02 10. Generalized Anxiety (GAD) 5:33 14. Generalized Anxiety (GAD) 4:46 9. Generalized Anxiety (GAD) 6:22 11. Intermittent Explosive (IED) 3:07 - - 10. Intermittent Explosive (IED) 3:33 12. Suicidality 0:49 15. Suicidality 0:39 11. Suicidality 0:37 17. Substance Use 6:33 16. Substance Use 5:23 17. Substance Use 5:43 13. Services 4:58 32. Services 3:16 13. Services 4:04 14. Pharmacoepidemiology 3:03 17. Pharmacoepidemiology 2:31 14. Pharmacoepidemiology 4:59 15. Demographics 3:06 - - 15. Demographics 6:32 16. Personality 5:15 18. Personality 5:21 16. Personality 1:46 18. Post-Traumatic Stress (PTSD) 10:05 19. Post-Traumatic Stress (PTSD) 9:06 18. Post-Traumatic Stress (PTSD) 10:33 19. Chronic Conditions 12:02 - - 20. Chronic Conditions 14:27 20. Neurasthenia 1:02 - - 19. Neurasthenia 0:49 21. 30-Day Functioning 6:55 - - 21. 30-Day Functioning 8:34 22. 30-Day Symptoms 7:27 20. 30-Day Symptoms 3:14 - - 23. Tobacco 3:46 21. Tobacco 0:36 - - 24. Eating Disorders 1:28 22. Eating Disorders 1:07 22. Eating Disorders 1:20 25. Premenstrual Syndrome 2:26 23. Premenstrual Syndrome 2:04 24. Premenstrual Syndrome 2:15 26. Obsessive-Compulsive (OCD) 2:53 24. Obsessive-Compulsive (OCD) 1:55 - - 27. Psychosis 2:38 25. Psychosis 2:19 25. Psychosis 2:48 28. Gambling 3:15 26. Gambling 1:14 - - 29. Worries and Unhappiness 3:29 - - - 30. Employment 10:06 6. Employment 5:34 26. Employment 11:44 31. Finances 3:52 - - 27. Finances 5:53 32. Marriage 4:44 - - 28. Marriage 4:21 33. Children 2:30 - - 29. Children 3:36 34. Social Networks 2:47 - - 30. Social Networks 2:49 35. Adult Demographics 6:30 - - 31. Adult Demographics 7:02 36. Childhood Demographics 3:95 - - 33. Childhood Demographics 0:34 37. Childhood 9:08 - - - - 38. Attention Deficit (ADHD) 3:09 28. Attention Deficit (ADHD) 3:23 - - 39. Oppositional-Defiant (ODD) 2:01 29. Oppositional-Defiant (ODD) 2:30 - - 40. Conduct (CD) 3:02 30. Conduct (CD) 2:55 34. Conduct (CD) 3:08 41. Separation Anxiety Disorder 4:24 31. Separation Anxiety Disorder 5:07 - - 42. Family Burden 2:31 - - - - 43. Perceptions of the Past 2:57 - - - - 44. Terror 1:06 38. Terror - - - 45. Respondent Contacts n/a - - - - 46. Interviewer Observations n/a 43. Interviewer Observations n/a 41. Interviewer Observations n/a 47. Dementia - paper only n/a 42. Dementia - paper only n/a - -
- For analyzing only NLAAS Latinos with Stata, you would use the nlswtlat in the svyset command.svyset seclustr [pweight=nlswtlat], strata(sestrat) vce(linearized) singleunit(certainty)
- The response rates for each of each component study of the CPES were:
- The National Comorbidity Survey Replication (NCS-R) response rate was 70.9%.
- The National Survey of American Life (NSAL) response rate was 72.3% overall and 70.7% for African Americans, 77.7% for Caribbean Blacks, and 69.7% for Whites.
- The National Latino and Asian American Study (NLAAS) response rate was 75.5% for the Latino surveys and 65.6% for the Asian surveys.
- When analyzing race groups that cross over more than one study (e.g., Latinos or Asians in all 3 studies, Blacks in NSAL and NCS-R), use the CPESWTSH or CPESWTLG weights. When excluding one of the studies in its entirety, use the appropriate paired weight. See CPES Weights Chart for more information.
- The total path length (not file name length) has to be less than 255 characters. Our file names can be lengthy. If the path to which you wish to extract your files is also lengthy, then WinZip will fail.Extract your files to the root directory of your hard drive. I.e., extract the files to c:/ instead of c:/User/My Documents/Various Social Science Projects On Which I Work/ICPSR Data/.
- Under normal operation the CPES Web site uses the HTTP protocol to deliver content. In a small number of cases we use HTTP with SSL encryption (commonly referred to as HTTPS) to protect the security of the data moving across the network. Our login procedure is one such case.When one tries to access a resource on the CPES Web site, the system checks for the presence of a login ticket (or, more generically, a cookie). If there is no ticket available, the browser is redirected to a URL (using HTTP) where the person enters a login and password. When the person clicks the Log In button, the login and password are delivered to the CPES Web site via HTTPS, and the Web site returns a login ticket via HTTPS. Finally the Web site returns the person to the original Web page or resource via HTTP. If anything goes wrong during this process, we deliver an error message about cookies not being enabled, which is the most common cause of failure. The next most common failure is when a site uses a proxy server or firewall, but only proxies HTTP, not HTTPS, and so the transaction fails.The workaround is to force the entire transaction through HTTPS. Here's an easy way to do that:
Please note that you cannot combine steps (1) and (3) by starting at a HTTPS-delivered version of the CPES home page, because you will still be redirected to an HTTP-type link for the login page after performing step (2). Thus step (3) will still be necessary, and it will also force many Web fetches to incur the SSL encryption overhead on both our server and your desktop machine.
- Go to this page: http://www.icpsr.umich.edu/mydata?path=CPES
- This should redirect you to the error page about cookies not being enabled. The URL in the "Address bar" should look like this: http://www.icpsr.umich.edu/ticketlogin.
- Modify the URL above, adding in an "s" between the "p" in "http" and the semicolon. It should now look like this: https://www.icpsr.umich.edu/ticketlogin
- Enter your MyData login and password, and click the Log In button. Or click the Log In Anonymously button.
- You should now have this URL in your "Address bar" (http://www.icpsr.umich.edu/mydata?path=CPES) and have a list of account-related actions you can take. The important thing, though, is that you now have a ticket (cookie) and should be able to download resources. If you click the CPES logo at the top of the page, that will return you to the CPES home page, and you can then use the Web site as usual.
- The field periods of three nationally representative surveys varied:
- Each study has its own Web site:
In addition, two issues of the International Journal of Methods in Psychiatric Research entitled "The NIMH Collaborative Psychiatric Epidemiology Surveys Initiative: Designs, Methods, and Instrumentation" were devoted to the CPES project. You can read the articles in those issues from the current CPES Web site :
- The National Comorbidity Survey Replication (NCS-R)
- The National Survey of American Life (NSAL)
- The National Latino and Asian American Study (NLAAS)
- Volume 13 Issue 2, Pages 57 - 139 (June 2004)
2. Original Articles
- Editorial (p 57-59). Lisa J. Colpe, Kathleen Merikangas, Bruce Cuthbert, Doreen Koretz, Karen Bourdon
- The National Comorbidity Survey Replication (NCS-R): background and aims (p 60-68). Ronald C. Kessler, Kathleen R. Merikangas [Link to PDF 22.214.171.124]
- The US National Comorbidity Survey Replication (NCS-R): design and field procedures (p 69-92). Ronald C. Kessler, Patricia Berglund, Wai Tat Chiu, Olga Demler, Steven Heeringa, Eva Hiripi, Robert Jin, Beth-Ellen Pennell, Ellen E. Walters, Alan Zaslavsky, Hui Zheng [Link to PDF 126.96.36.199]
- The World Mental Health (WMH) Survey Initiative version of the World Health Organization (WHO) Composite International Diagnostic Interview (CIDI) (p 93-121). Ronald C. Kessler, T. Bedirhan Üstün [Link to PDF 188.8.131.52]
- Clinical calibration of DSM-IV diagnoses in the World Mental Health (WMH) version of the World Health Organization (WHO) Composite International Diagnostic Interview (WMH-CIDI) (p 122-139). Ronald C. Kessler, Jamie Abelson, Olga Demler, Javier I. Escobar, Miriam Gibbon, Margaret E. Guyer, Mary J. Howes, Robert Jin, William A. Vega, Ellen E. Walters, Philip Wang, Alan Zaslavsky, Hui Zheng [Link to PDF 184.108.40.206]
1. Guest editorial
- Volume 13 Issue 4, Pages 193 - 298 (November 2004)
2. Original Articles
- Guest editorial (p 193-195). Lisa Colpe, Kathleen Merikangas, Bruce Cuthbert, Karen Bourdon [Link to PDF 220.127.116.11]
- The National Survey of American Life: a study of racial, ethnic and cultural influences on mental disorders and mental health (p 196-207). James S. Jackson, Myriam Torres, Cleopatra H. Caldwell, Harold W. Neighbors, Randolph M. Nesse, Robert Joseph Taylor, Steven J. Trierweiler, David R. Williams [Link to PDF 18.104.22.168]
- Considering context, place and culture: the National Latino and Asian American Study (p 208-220). Margarita Alegria, David Takeuchi, Glorisa Canino, Naihua Duan, Patrick Shrout, Xiao-Li Meng, William Vega, Nolan Zane, Doryliz Vila, Meghan Woo, Mildred Vera, Peter Guarnaccia, Sergio Aguilar-gaxiola, Stanley Sue, Javier Escobar, Keh-ming Lin, Fong Gong [Link to PDF 22.214.171.124]
- Sample designs and sampling methods for the Collaborative Psychiatric Epidemiology Studies (CPES) (p 221-240). Steven G. Heeringa, James Wagner, Myriam Torres, Naihua Duan, Terry Adams, Patricia Berglund [Link to PDF 126.96.36.199].
- The development and implementation of the National Comorbidity Survey Replication, the National Survey of American Life, and the National Latino and Asian American Survey (p 241-269). Beth-Ellen Pennell, Ashley Bowers, Deborah Carr, Stephanie Chardoul, Gina-qian Cheung, Karl Dinkelmann, Nancy Gebler, Sue Ellen Hansen, Steve Pennell, Myriam Torres [Link to PDF 188.8.131.52]
- Cultural relevance and equivalence in the NLAAS instrument: integrating etic and emic in the development of cross-cultural measures for a psychiatric epidemiology and services study of Latinos (p 270-288). Margarita Alegria, Doryliz Vila, Meghan Woo, Glorisa Canino, David Takeuchi, Mildred Vera, Vivian Febo, Peter Guarnaccia, Sergio Aguilar-Gaxiola, Patrick Shrout [Link to PDF 184.108.40.206]
- Methodological innovations in the National Survey of American Life (p 289-298). James S. Jackson, Harold W. Neighbors, Randolph M. Nesse, Steven J. Trierweiler, Myriam Torres [Link to PDF 220.127.116.11]
- One question asks about the sexual orientation of the respondent in the NCS-R and NLAAS surveys. Please fine the variable "CN11_3" in the Interactive Codebook. For the frequencies of this variable for each survey, please find the variable, and click the "view the summary statistics and/or frequencies" in the Web site and see the further information!
This variable is only available in the restricted-use versions of these data files. Please see also variable "CN11_3" in the list of restricted variables.
- The "Representative of the Receiving Organization" refers to an individual who has the authority to represent your organization in agreements of this sort, such as a Vice President, Dean, Provost, Center Director, or similar official. (Note that a Department Chair is not acceptable unless specific written delegation of authority exists.)
- Weighted and unweighted frequencies and an example of an NCSR subpopulation analysis.
NCS-R adopts the practice of normalizing its analysis weights. This is accomplished by multiplying the original population scale weight by a factor of k=n/sum(population weights for all sample cases). Analysis results for all statistics of interest (except population totals) do not change under this or any other linear scaling of the weights.
In any weighted data set, the weighted frequencies are meaningless because the data producer can scale these values to any total value that they choose. The common practice of normalizing weights, used by NCS-R, scales the sum of the analysis weights to the unweighted sample size, n. The observation that weighted counts are less than unweighted counts suggests to me that the population weights for the cases included in this analysis were on average less than the average of weights for the full sample. In short, this is a good observation and it was an important question to ask. I recommend that analysts always produce tables of statistics that show the unweighted n, the weighted estimate of the statistics of interest, and estimated standard errors or confidence intervals that reflect the effect of weighting as well as the design stratification and clustering on the sampling variance of estimates.
It is possible that the weighted frequency for a given cell might be lower than the unweighted cell since the weights are non-integer and some are less than 1. Below is a SAS PROC MEANS analysis of the weight for the part 2 NCSR data as an illustration of how this happens but overall, the sum of weights is still n=5692. (Part 2 of the NCSR).
The example also demonstrates how to correctly analyze a subpopulation of those with 12 MDDH in the NCSR data set. An implied domain statement is used in PROC SURVEYFREQ of SAS v9.2 for analysis of the selected subpopulation. The way this is accomplished is to use the domain variable as the first variable in the tables statement of PROC SURVEYFREQ (see SAS v9.2 documentation for more details on PROC SURVEYFREQ and domain analysis).
* NOTE: V07655 IS THE DSM 12 MONTH MDDH INDICATOR VARIABLE FROM THE CPES DATA SET;
* THIS VARIABLE IS LISTED FIRST IN THE TABLES STATEMENT BELOW AND FUNCTIONS AS A DOMAIN VARIABLE;
* DATA USED IS THE FULL CPES DATA SET WITH THE NCSR PART 2 WEIGHT;
proc surveyfreq data=CPES;
STRATA SESTRAT ;
CLUSTER SECLUSTR ;
tables V07655*RANCEST /row chisq;
The SURVEYFREQ Procedure
Number of Strata 42
Number of Clusters 84
Number of Observations 20013
Number of Observations Used 5692
Number of Obs with Nonpositive Weights 14321
Sum of Weights 5692.0038
Table of V07655 by RANCEST
Weighted Std Dev of Std Err of
V07655 RANCEST Frequency Frequency Wgt Freq Percent Percent
1 4 10 5.65100 1.99781 0.0993 0.0363
8 62 37.33360 6.56090 0.6559 0.1217
10 71 35.42600 5.15569 0.6224 0.1006
11 474 289.57490 25.29687 5.0874 0.3079
12 29 14.54000 3.34056 0.2554 0.0549
Total 646 382.52550 25.57003 6.7204 0.3112
5 4 73 88.97570 14.76961 1.5632 0.2744
8 465 592.67140 60.34542 10.4124 1.1330
10 646 668.49300 53.64654 11.7444 0.9919
11 3706 3852 234.29613 67.6654 1.6432
12 156 107.82340 13.40303 1.8943 0.2469
Total 5046 5309 233.24960 93.2796 0.3112
Total 4 83 94.62670 15.56364 1.6624 0.2909
8 527 630.00500 61.94072 11.0682 1.1746
10 717 703.91900 54.99826 12.3668 1.0356
11 4180 4141 255.08542 72.7528 1.8167
12 185 122.36340 14.66705 2.1497 0.2628
Total 5692 5692 251.09597 100.000
PROC MEANS DATA=CPES;
CLASS V07655 RANCEST;
WHERE NCSRWTLG NE .; *SELECT ONLY THOSE WITH NON-MISSING ON THE NCSR PART 2 WEIGHT ;
The MEANS Procedure
Analysis Variable : NCSRWTLG NCSR sample part 2 weight
(12Mo) Ancestry N Obs N Mean
1 4 10 10 0.5651000
8 62 62 0.6021548
10 71 71 0.4989577
11 474 474 0.6109175
12 29 29 0.5013793
5 4 73 73 1.2188452
8 465 465 1.2745622
10 646 646 1.0348189
11 3706 3706 1.0392647
12 156 156 0.6911756
- The CPES weights take into account unequal probabilities of selection, characteristics of non-respondents, and post-stratification. Weighting for unequal probabilities of selection reduced selection bias. Non-response was accounted for using geographic factors. Demographic factors such as age, gender, and census region were used to calculate the post-stratification weights, ensuring that the distribution of the sample resembles the distribution of the U.S. on these demographic characteristics. All of these adjustments result in the weighted CPES sample being representative of the race and ethnic groups included in the study, that is, no group is over- or underrepresented. See CPES Weights Chart for more information.
- It appears that newer versions of the Acrobat software apply formatting that occasionally fails to translate properly in older versions of the program. CPES tests documentation files to ensure compatibility with the latest version of the free Acrobat Reader. We suggest downloading the latest version of the free Acrobat Reader from Adobe's Web site.
- The National Comorbidity Survey Replication (NCS-R) Part 1 included a core diagnostic assessment of all 9,282 respondents and Part 2 was administered only to 5,692 of the 9,282 Part 1 respondents, including all Part 1 respondents with a lifetime disorder plus a probability subsample of other respondents. See NCS-R Part 1 and 2 Sample for more information. See Final Weights and Special Analysis Considerations for Weighted Analysis in the Weighting section of About CPES for an explanation of the two parts and the implications for weighting analyses.
Since the NCS-R obtained rich data on White respondents, and due to the high cost of obtaining interviews, it was felt that it was not necessary to obtain additional data on White respondents in the NSAL. The data on the NCS-R Whites is available now that the data have been merged.
- Data files must be uncompressed before they can be used.ICPSR "cart" files are zipped with WinZip. If the downloaded cart file is represented with a vice-grips folder icon, the computer has WinZip installed. In this case, extract the files from the cart file with WinZip. If the cart file is represented with a folder icon that has a zipper on the left-hand side of the folder, WinZip is not installed and the XP operating system will treat the cart file as a compressed folder. But since the files are actually compressed in a WinZip archive file, the XP operating system is not able to provide the files to other applications (as it is able to do with files located in a standard compressed folders). Files can be extracted from the WinZip archive files that appear to be compressed folders by moving the nested folders and/or files to an uncompressed folder.If you are using a computer that does not have WinZip installed, and are having difficulty accessing the data files, check with your school's IT department or the computer lab where you are working to learn what uncompressed directory to use. Move the downloaded cart file to that directory, and extract the compressed files there. Once the data files are extracted, they should be accessible to the statistical application.If you chose to save the downloaded zipped files to a removable media such as a CD, or jump drive, be aware that the compression issue may still need to be addressed.The statistical application still does not see the data file. What else could it be?Some statistical applications have a limit on the number of characters that can be used to specify a file location. The default folder hierarchy in which ICPSR distributes its files comprises at least three levels. If this folder hierarchy is extracted to a folder that is already nested within several other folders, the length of the resulting drive, folder hierarchy, and filename specification could exceed that which is usable by the statistics application. In cases such as this, ICPSR recommends that the lowest folder in the hierarchy be moved or copied to a location as high in the folder hierarchy as possible and that this new location be specified in the setup files.
- Data files must be uncompressed before they can be used.ICPSR files are zipped with WinZip. If the downloaded file is represented with a vice-grips folder icon, the computer has WinZip installed. In this case, extract the files from the file with WinZip. If the file is represented with a folder icon that has a zipper on the left-hand side of the folder, WinZip is not installed and the XP operating system will treat the file as a compressed folder. But since the files are actually compressed in a WinZip archive file, the XP operating system is not able to provide the files to other applications (as it is able to do with files located in a standard compressed folders). Files can be extracted from the WinZip archive files that appear to be compressed folders by moving the nested folders and/or files to an uncompressed folder.If you are using a computer that does not have WinZip installed, and are having difficulty accessing the data files, check with your school's IT department or the computer lab where you are working to learn what uncompressed directory to use. Move the downloaded file to that directory, and extract the compressed files there. Once the data files are extracted, they should be accessible to the statistical application.If you chose to save the downloaded zipped files to a removable media such as a CD, or jump drive, be aware that the compression issue may still need to be addressed.The statistical application still does not see the data file. What else could it be?Some statistical applications have a limit on the number of characters that can be used to specify a file location. The default folder hierarchy in which ICPSR distributes its files comprises at least two levels. If this folder hierarchy is extracted to a folder that is already nested within several other folders, the length of the resulting drive, folder hierarchy, and filename specification could exceed that which is usable by the statistics application. In cases such as this, ICPSR recommends that the lowest folder in the hierarchy be moved or copied to a location as high in the folder hierarchy as possible and that this new location be specified in the setup files.
- There are couple reasons why the number of cases will not be consistent across all variables:
- Some questions were asked in one study and not in the others. See "Are all questions asked of all respondents?."
- Several different versions of the instrument were used in the component surveys, with the result that not all respondents answered every question. Thus, the number of cases will not be consistent across all variables. In terms of questionnaire versions, NCS-R had 15, NSAL had 14, and NLAAS had 8.
- We are sorry but the volume of questions of this nature exceeds the resources we have available for these requests. Also, some changes were made to the data after some papers were written making it impossible to fully replicate some of the findings.The master CPES data sets are updated periodically as various, typically small, errors are detected. Diagnostic algorithms are periodically updated as well. This updating will continue in the future as needed and public users will be informed of these updates. It is important for public users to recognize that, because of these changes, it will not always be possible to reproduce results reported in earlier publications.
- When using the NSAL weighted data using the NSALWTCT weight, it centers the sample size to the proportion that the three race groups exist in NSAL?s sample population, that is, where African Americans live plus where Caribbeans live and Whites in areas where 10% or more of the population is Black. Therefore, when these weights are applied, the NSAL White weighted sample size increases and the two Black samples decrease.
In the past when most analysts did not correct the standard errors for complex survey design, this posed analytical challenges since analyses assuming a simple random sample used the number of cases to determine the significance of the analyses (chi-squares, regressions, etc). The common solution was to center the weights to each of the race?s sample size in order to have a large enough sample size by race when looking at race differences. But with complex design correction, the numbers of strata and clusters are used instead the number of cases to determine significance. Therefore, the small N by race does not affect the analyses. Using the NSAL Population weight NSALWTPN instead of NSALWTCT will result in very large population N?s but the same analyses results.
- Please consult the Diagnosis section of the NCS/NCS-R Web site for a description of the criteria used for each diagnosis. Also please check the PTSD interview schedule. In the NCS-R and NLAAS, people with only one event reported skip to PT118 and are asked about this one event (this is the Random Event section). For people who have more than one event we ask what they consider to be their worst event and then we select a random event to ask about. If the worst event and the random event are the same occurrence of the same event, they are skipped to PT121a and asked about it as a random event. Therefore, the only people asked PT68-PT106 are those who had multiple events or multiple occurrences of one event and the randomly selected event was different from the worst event. We evaluate both events, and if they meet full criteria for the worst event or they meet full criteria for the random event then they meet full criteria for PTSD. In the NSAL, only the worst event was used to determine if they meet full criteria.
- The Suicidality section has a skip at the very beginning (SD1). If the respondent was able to read, they were asked SD2-SD14, if not, they were asked SD15-SD27. Therefore, you need to combine the data from this series, e.g., combine V01995 and V02025, etc. Please also note that these questions were not asked of the entire NSAL sample (only African-American respondents were asked this in NSAL).
- For many Internet Explorer users, the default text display is Smaller, which means the text in your Web browser is displaying smaller than CPES has requested. As such, it probably looks very small to you. This is easily remedied. In IE, select the View menu and go down to Text View or Text Zoom. From there you can set your text size to Largest, Larger, Normal, Smaller, and Smallest. It's probably set to Smaller by default. Choose Normal and you should have no further problems.CPES designs its site so that the user can control the font size. By doing this, CPES guarantees that users with low vision can access our content.
- We anticipate that changes will be made to the algorithms in the future. We plan to update them no more than every six months.
- No. American Indians in the CPES were too small to be in a category of its own and were combined with other races with a small sample size.