Rare Events, Sample Size, and Statistical Problems in the Analysis of the NCS (National Crime Survey) City Surveys

• NCJ Number: 102770
• Journal: Journal of Criminal Justice Volume: 14 Issue: 5 Dated: (1986) Pages: 441-448
• Author(s): R M O'Brien
• Date Published: 1986
• Length: 8 pages
• Publication Format: Article
• Publication Type: Report (Study/Research)
• Language: English
• Country: United States of America
• Note: *This document is currently unavailable from NCJRS.

Annotation

The National Crime Survey (NCS) city surveys are a unique and important data set and the only practical alternative to Uniform Crime Reports-based crime rate estimates available to criminologists for a large number of American cities.

Abstract

There are, however, some statistical problems involved in using this particular data set that are quite different from those usually faced by researchers investigating crime rates across cities. These result from the relative rareness of many of the crimes investigated and the small number of cities included in these surveys. These problems include the unreliability of rate estimates for cities and the potential for both lack of statistical power and overfitting of equations designed to explain differences in crime rates among cities. Each of these problems is explicated, and strategies for analyzing these data are suggested. (Author abstract)