National Crime Victimization Survey Instrument Redesign Field Test - Condition 3A Address Based Sample Web Survey, [United States], 2022 (ICPSR 39166)

Version Date: Jul 30, 2026

Cite this study |

Principal Investigator(s):
United States. Bureau of Justice Statistics; Westat

Series:

https://doi.org/10.3886/ICPSR39166.v1

Version V1

Slide tabs to view more

Summary

The Bureau of Justice Statistics initiated a multiyear effort to improve the efficiency, reliability, and utility of the National Crime Victimization Survey (NCVS). The effort had three main goals: modernize the organization and content of the NCVS instrument, increase the quality of information collected and efficiency of the instrument flow, and improve the measurement and classification of crime. To that end, BJS is redesigning the entire survey instrument, which includes a household roster, a victimization screener, and a detailed crime incident report (CIR). Each of these instrument components were examined in the NCVS Instrument Redesign Field Test. The initial large-scale national field test was conducted from October 2019 to March 2020 to compare the performance of the current NCVS instrument and procedures (Condition 1) against the redesigned instrument (Condition 2).

After the large-scale field test, a smaller test was conducted that assessed the feasibility of conducting the NCVS as a self-administered, web-based instrument. This test included two samples: an address based sample (Condition 3A) and a sample of individuals who were part of an existing web-based panel (Condition 3B). For more details on this effort, see the NCVS Instrument Redesign webpage.

Citation

United States. Bureau of Justice Statistics, and Westat. National Crime Victimization Survey Instrument Redesign Field Test - Condition 3A Address Based Sample Web Survey, [United States], 2022. Inter-university Consortium for Political and Social Research [distributor], 2026-07-30. https://doi.org/10.3886/ICPSR39166.v1

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote

Funding

United States Department of Justice. Office of Justice Programs. Bureau of Justice Statistics

Subject Terms

Geographic Coverage

Smallest Geographic Unit

None

Restrictions

This data collection may not be used for any purpose other than statistical reporting and analysis. Use of these data to learn the identity of any person or establishment is prohibited.

Distributor(s)

Inter-university Consortium for Political and Social Research
Hide

Time Period(s)

2022-01 -- 2022-05

Date of Collection

2022-01 -- 2022-05

Data Collection Notes

  1. The National Crime Victimization Survey Instrument Redesign Field Test Web Test included two samples: an address based sample (Condition 3A) and a sample of individuals from a probability based web panel (Condition 3B). While the same instrument was used for both surveys, the Condition 3A Address Based Sample Web Survey (ICPSR 39166) and the Condition 3B Web Based Panel Web Survey (ICPSR 39321) were released as separate studies.

  2. The Bureau of Justice Statistics (BJS) completed a multiyear effort to improve the efficiency, reliability, and utility of the NCVS. This effort included redesigning the entire survey instrument. The new instrument was examined and tested in the NCVS Instrument Redesign Field Test. The four studies included in the National Crime Victimization Survey (NCVS) Instrument Redesign Series are from this large-scale national field test and are designed to support research and development efforts. These data will not be used to produce official BJS statistics. For additional information on the NCVS Instrument Redesign and BJS-funded reports analyzing these data, please visit the NCVS Instrument Redesign website.

Hide

Sample

The sampling procedure for the Condition 3A (C3A) address based (ABS) web test was similar to the methods used for the Condition 2 Field Test. The potential universe for the NCVS Instrument Redesign Field Test was all persons age 12 or older living in households in the 48 contiguous States and the District of Columbia. Persons living in Alaska and Hawaii and those living in group quarters were excluded from the universe for operational efficiency and cost. The Field Test employed a stratified three-stage sample design: (1) selection of primary sampling units (PSUs), individual counties or groups of counties; (2) selection of secondary sampling units (SSUs), census tracts or groups of census tracts within sampled PSUs; and (3) selection of households within sampled SSUs.

The C3A sample was designed to yield a target of 3,000 completed surveys. Assuming an 8% nondeliverable rate, an average of 2.3 age-eligible persons per household, a 35% screener response rate, and a 60% extended survey response rate, a total sample size of 6,752 addresses was selected. All sampled addresses were mailed a request to do the web survey. The initial mailing asked a knowledgeable individual to fill out web-based roster of those living in the household. Once the roster was completed, all eligible persons 18 and over were mailed a survey request. At the same time, the parents of those ages 12 to 17 were asked for permission to contact the minors to do the survey.

Universe

Individuals age 12 years of age or older living in households within the contiguous United States

Unit(s) of Observation

Crime Incident, Individual, Household

Data Type(s)

Mode of Data Collection

Response Rates

For Condition 3A (ABS Web survey), 29.6 percent of rosters were completed. Of these households, 71.3 household respondents completed their individual surveys along with 48.3 percent of other adults in the household and 33.3 percent of youth respondents.

Hide

Original Release Date

2026-07-30

Version History

2026-07-30 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:

  • Checked for undocumented or out-of-range codes.

Hide

Weight

Household, person, and victimization data from the ABS Web Test sample were adjusted to provide annual estimates of victimizations experienced by the U.S. population age 12 or older. Final weights and replicate weights on the Condition 3A (ABS) data files include:

In the household level file:

  • HH_PSWT0 is the final raked and trimmed household weight.
  • HH_PSWT1 thru HH_PSWT80 are the trimmed household replicate weights.

In the person level file:

  • SP_RKWT0 is the final raked and trimmed person level weight.
  • SP_RKWT1 thru SP_RKWT80 are the trimmed person level replicate weights.
  • HH_PSWT0 is the final raked and trimmed household weight.
  • HH_PSWT1 thru HH_PSWT80 are the trimmed household replicate weights.

In the incident level file:

  • INC_WGT0 is the weight constructed for incident level analysis.
  • INC_WGT1 thru INC_WGT80 are the replicate weights.

In the ABS web test analyses, the following weights were used:

For household-level victimization rates

  • Numerator: Compute the number of household victimizations by summing the household victimization weight across all household crime incident records on the incident level file. Compute the household victimizations as shown below:

    For the full C3A sample, this weight is INC_WGT0

    For records that represent household level crimes (this includes household crimes TOCE equal 31 thru 60), this weight (INC_WGT0) was created by multiplying the weight of the household respondent (i.e., HH_PSWT0) times the Series size (SERIESCT) (where applicable - if the record represents a single incident, then Series was set to '1'). Series were capped at 10 for purposes of weighting.

    For variance estimation, use the same procedures for the replicate weights: INC_WGT1 - INC_WGT80

  • Denominator: Compute the number of households by summing HH_PSWT0 across all the household records on the household level file.

    For variance estimation, use the same procedures for the replicate weights: HH_PSWT01 - HH_PSWT080

  • To get the household victimization rate, divide the numerator by the denominator.

Person-level victimization rates

Analysis of the full C3A sample:

  • Numerator: Compute the number of personal victimizations by summing the personal victimization weight across all personal crime incident records on the incident level file. Compute the personal victimization weight as shown below:

    For the full C3A sample, this weight is INC_WGT0

    For records that represent person level crimes (this includes person crimes TOCE equals 1 thru 26), this weight (INC_WGT0) was calculated by multiplying the weight of the sampled respondent (i.e., SP_RKWT0) times the Series size (SERIESCT) (where applicable - if the record represents a single incident, then Series was set to '1'). Series were capped at 10 for purposes of weighting.

    For variance estimation, use the same procedures for the replicate weights: INC_WGT1 - INC_WGT80

  • Denominator: Compute the number of households by summing SP_RKWT0 across all the person records on the person level file.

    For variance estimation, use the same procedures for the replicate weights: SP_RKWT01 - SP_RKWT80

  • To get the personal victimization rate, divide the numerator by the denominator.

Hide

Notes

  • 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.

  • ICPSR usually offers files in multiple formats for researchers to be able to access data and documentation in formats that work well within their needs. If you have questions about the accessibility of materials distributed by ICPSR or require further assistance, please visit ICPSR’s Accessibility Center.