Comparing Measures of Crime: Police Statistics and Survey Estimates of Citizen
Victimization in American Cities. Proceedings of the American Statistical Association,
Social Statistics Section, 1974.
The growing use of sample surveys to measure the volume and distribution of crime in the
United States will provide social scientists and police administrators with valuable new data with
which to test their theories and plan crime-reduction programs. One use of the surveys has
been to compare them to official statistics. Reports released by the Law Enforcement
Assistance Administration have stirred public interest by their contrast with police figures on
crime and the type summarized in the FBI’s yearly Uniform Crime Report. Such comparisons
inevitably reveal wide gaps between rates registered by the two sources. This type of analysis
has been encouraged by the government’s decision to calculate UCR-compatible figures from
citizen surveys, although this is perhaps the least useful application of the data. Survey and
police crime-measurement procedure produce different figures, but the reasons for this and its
implications require analysis. A discussion of how survey and official crime statistics differ and
why we obtain these discrepancies may clarify both their comparability and their individual
interpretation, and it may speak to their improvement in the future. There is a detailed
discussion of the crime measurement process on both the police and survey sides of the
Crime Reporting