The following HTML text is provided to enhance online
readability. Many aspects of typography translate only awkwardly to HTML.
Please use the page image
as the authoritative form to ensure accuracy.
Surveying Victims: Options for Conducting the National Crime Victimization Survey
Recommendation 4.2:Changing from a 6-month reference period to a 12-month reference period has the potential for improving the precision per-unit cost in the NCVS framework, butthe extent of loss of measurement quality is not clear from existing research based on the post-1992-redesign NCVS instrument.BJS should sponsor additional research—involving both experimentation as well as analysis of the timing of events in extantdata—to inform this trade-off.
Recommendation 4.3:BJS should make supplements a regularfeature of the NCVS. Procedures should be developed for soliciting ideas for supplements from outside BJS and for evaluatingthese supplements for inclusion in the survey.
Recommendation 4.4:BJS should maintain the core set ofscreening questions in the NCVS but should consider streamlining the incident form (either by eliminating items or by changingtheir periodicity).
Recommendation 4.5:BJS should investigate the use of modeling NCVS data to construct and disseminate subnational estimates of major crime and victimization rates.
Recommendation 4.6:BJS should develop, promote, and coordinate subnational victimization surveys through formula grantsfunded from state-local assistance resources.
Recommendation 4.7:BJS should investigate changing the sample design to increase efficiency, thus allowing more precision fora given cost. Changes to investigate include:
changing the number or nature of the first-stage samplingunits;
changing the stratification of the primary sampling units;
changing the stratification of housing units;
selecting housing units with unequal probabilities, sothat probabilities are higher where victimization rates arehigher; and
alternative person-level sampling schemes (sampling orsubsampling persons within housing units).
Recommendation 4.8:BJS should investigate the introduction ofmixed mode data collection designs (including self-administeredmodes) into the NCVS.