National Social Life, Health and Aging Project (NSHAP): Wave 3, [United States], 2015-2016 (ICPSR 36873)
Version Date: Mar 8, 2019 View help for published
Principal Investigator(s): View help for Principal Investigator(s)
Linda Waite, University of Chicago. Department of Sociology; Kathleen Cagney, University of Chicago. Department of Sociology, and Department of Health Studies; William Dale, University of Chicago. Department of Medicine. Section of Geriatrics and Palliative Medicine; Louise Hawkley, University of Chicago; Elbert Huang, University of Chicago. Department of Medicine; Diane Lauderdale, University of Chicago; Edward O. Laumann, University of Chicago. Department of Sociology; Martha McClintock, University of Chicago. Department of Psychology, and Department of Comparative Human Development; Colm O'Muircheartaigh, Irving B. Harris Graduate School of Public Policy Studies; L. Philip Schumm, University of Chicago. Department of Health Studies
Version V4 (see more versions)
Alternate Title View help for Alternate Title
Summary View help for Summary
The National Social Life, Health and Aging Project (NSHAP) is a population-based study of health and social factors on a national scale, aiming to understand the well-being of older, community-dwelling Americans by examining the interactions among physical health, illness, medication use, cognitive function, emotional health, sensory function, health behaviors, and social connectedness. It is designed to provide health providers, policy makers, and individuals with useful information and insights into these factors, particularly on social and intimate relationships. The National Opinion Research Center (NORC), along with Principal Investigators at the University of Chicago, conducted more than 3,000 interviews during 2005 and 2006 with a nationally representative sample of adults aged 57 to 85. Face-to-face interviews and biomeasure collection took place in respondents' homes. Wave 3 was conducted from September 2015 through November 2016, where 2,409 surviving Wave 2 respondents were reinterviewed, and a New Cohort consisting of adults born between 1948 and 1965 together with their spouses or coresident partners was added. All together, 4,777 respondents were interviewed in Wave 3. The following files constitute Wave 3: Core Data, Social Networks Data, Disposition of Returning Respondent Partner Data, and Proxy Data.
Included in the Core files (Datasets 1 and 2) are demographic characteristics, such as gender, age, education, race, and ethnicity. Other topics covered respondents' social networks, social and cultural activity, physical and mental health including cognition, well-being, illness, history of sexual and intimate partnerships and patient-physician communication, in addition to bereavement items. In addition data on a panel of biomeasures including, weight, waist circumference, height, and blood pressure was collected. The Social Networks (Datasets 3 and 4) files detail respondents' current relationship status with each person identified on the network roster. The Disposition of Returning Respondent Partner (Datasets 5 and 6) files detail information derived from Section 6A items regarding the partner from Waves 1 and 2 within the questionnaire. This provides a complete history for respondent partners across both waves. The Proxy (Datasets 7 and 8) files contain final health data for Wave 1 and Wave 2 respondents who could not participate in NSHAP due to disability or death
NACDA also maintains a Colectica portal with the NSHAP Core data across waves 1-3, which allows users to interact with variables across waves and create customized subsets. Registration is required.
Citation View help for Citation
Funding View help for Funding
Subject Terms View help for Subject Terms
Geographic Coverage View help for Geographic Coverage
Smallest Geographic Unit View help for Smallest Geographic Unit
Restrictions View help for Restrictions
Public and restricted versions of all datasets are included in this collection. Users interested in obtaining the restricted versions of these data from NACDA must request and complete the NSHAP Restricted Data Use Agreement form. Users can download this form from the download page associated with this dataset. Completed PDF forms with original signature(s) should be emailed to firstname.lastname@example.org.
Distributor(s) View help for Distributor(s)
Time Period(s) View help for Time Period(s)
Date of Collection View help for Date of Collection
Data Collection Notes View help for Data Collection Notes
This collection is being released in ten parts. Parts 1 through 8 contain the ICPSR-processed files; Parts 9 and 10 contain the original Stata data files with extended and nonextended missing values provided by the P.I. in a zip file package.Please refer to the related data collections ICPSR 20541 and ICPSR 34921, National Social Life, Health, and Aging Project (NSHAP): Waves 1 and 2 for further information regarding the NSHAP project.
For further information about the National Social Life, Health, and Aging Project (NSHAP), please see the NORC at the University of Chicago Web site.Users can subscribe to the NSHAP data mailing list at the University of Chicago NSHAP List website.
The identification variable SU_ID can be used to link the respondent records across the waves of the survey.
The grant numbers have been updated as of September 2019; users citing the NSHAP data should ensure their citations are up to date.
Study Design View help for Study Design
As in Wave 2, all questions were asked entirely in the in-person interview or the leave-behind questionnaires. In Wave 3, though, there are separate leave-behind questionnaires for the new cohort and original cohort. Users can refer to the related data collections ICPSR 20541 and ICPSR 34921, National Social Life, Health, and Aging Project (NSHAP): Waves 1 and 2 for further study design information, as well as the Original P.I. Documentation in the ICPSR Codebook and visit the NORC at the University of Chicago Web site.
Sample View help for Sample
Although the New Cohort added in Wave 3 was selected from a national frame, it was not the same as that used to select the Original Cohort. As with the Original Cohort, the New Cohort was obtained from a probability sample of U.S. adults meeting the age criteria, with African-Americans and Hispanics sampled at a higher rate. Spouses or coresident partners of sampled respondents were also included. Users may refer to ICPSR 20541 and ICPSR 34921, National Social Life, Health, and Aging Project (NSHAP): Waves 1 and 2 for further sampling information, as well as the Original P.I. Documentation in the ICPSR Codebook and visit the NORC at the University of Chicago Web site.
Time Method View help for Time Method
Universe View help for Universe
Community dwelling individuals ages 24 to 97 in the United States. Wave 2 respondents were reinterviewed, and a New Cohort consisting of adults born between 1948 and 1965 together with their spouses or coresident partners was added.
Unit(s) of Observation View help for Unit(s) of Observation
Method of Data Collection View help for Method of Data Collection
Mode of Data Collection View help for Mode of Data Collection
Original Release Date View help for Original Release Date
Version History View help for Version History
2019-03-08 This collection was updated to include resupplied restricted versions as well as public versions of the Core Data, Social Networks Data, Disposition of Returning Respondent Partner Data, and the Original NSHAP Wave 3 Data Files. Public and restricted versions of Proxy Data have also been added to the collection.
2018-04-26 Study has been updated to fully curate previously expedited release of study.2018-02-15 The citation of this study may have changed due to the new version control system that has been implemented. The previous citation was:
- Waite, Linda, Kathleen Cagney, William Dale, Louise Hawkley, Elbert Huang, Diane Lauderdale, Edward O. Laumann, Martha McClintock, Colm O'Muircheartaigh, and L. Philip Schumm. National Social Life, Health and Aging Project (NSHAP): Wave 3, [United States], 2015-2016. ICPSR36873-v4. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2019-03-08. http://doi.org/10.3886/ICPSR36873.v4
2017-10-25 The readme file was included as a publicly available document; the version number for this collection will not be changed as this was an oversight during the initial release.
2017-10-25 ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:
- Standardized missing values.
- Checked for undocumented or out-of-range codes.
Weight View help for Weight
The data are not weighted, but contain two weight variables within the Part 1 Core data file, which users may wish to apply during analysis. Respondent-level weights representing the inverse probability of selection are contained in the variable WEIGHT_SEL. A second set of weights incorporating a non-response adjustment based on age and urbanicity is contained in the variable WEIGHT_ADJ. Both sets of weights are scaled to sum to the final sample size (3,005).
As noted above, in each NSHAP wave there is a variable called WEIGHT_ADJ which is non-missing for all respondents in that wave, and which adjusts for differing probabilities of selection as well as differential non-response. These weight variables should be used for all cross-sectional analyses. Please note that the WEIGHT_ADJ variable differs across waves (since the selection probabilities and non-response vary across waves).
With respect to longitudinal analyses, NSHAP does not yet have a true panel weight (currently in progress). The Wave 2 weight variable (WEIGHT_ADJ) should be used for longitudinal analyses until the panel weight is created. The wave 2 weight is non-missing for all but 38 respondents with data for multiple (i.e., at least two) waves. Thus, this weight is adequate for longitudinal analyses using the subset of respondents with data from Wave 2 and/or at least two waves (this includes many typical longitudinal analyses). It is not advised to use this weight variable for those cases where someone wishes to include those respondents with data from only one wave, except for those with data only from Wave 2).
The public-use data files in this collection are available for access by the general public. Access does not require affiliation with an ICPSR member institution.