U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Social and Scientific Influences on the Measurement of Criminal Victimization

NCJ Number
211566
Journal
Journal of Quantitative Criminology Volume: 21 Issue: 3 Dated: September 2005 Pages: 245-266
Author(s)
Janet L. Lauritsen
Date Published
September 2005
Length
22 pages
Annotation
This paper examines how social and scientific factors have influenced the measurement properties of the National Crime Victimization Survey (NCVS).
Abstract
The paper first summarizes the characteristics of the NCVS, noting that its general form and content reflect decades of research by Federal agencies, academics, and review panels. This is followed by a discussion of methodological changes in the NCVS linked to budget constraints, namely, the change from in-person interviews to telephone interviews; sample size reductions; the elimination of some questions, such as the lifestyle items; and the addition of other items, such as public-housing and university-housing residence. The paper then turns to an examination of methodological changes in the NCVS influenced by social factors. The two major changes in this regard are the addition of items for recording hate-related victimization and the addition of items that record respondent disabilities, so as to estimate criminal victimization against the disabled. In assessing the impact on the NCVS of budget constraints and the addition of new questions, the paper notes that the NCVS sample size is now smaller than at any point in the survey's history. Even the most methodologically stringent practices may not result in a reliable set of measures if the crime of interest is rare relative to sample size. This problem is likely to arise with the hate-crime estimates, especially when determining whether annual changes or subgroup differences are statistically significant. An increase in sample size is unlikely given budget constraints. Further, additional questions add time to the interview, and the length of the interview is an important determinant of cost. Thus, budget constraints inevitably influence both the comprehensiveness and the reliability of NCVS data. 23 references and appended hate-crime and disability-related NCVS questions