VALIDITY OF OFFICIAL CRIME STATISTICS - AN EMPIRICAL INVESTIGATION

• NCJ Number: 18305
• Author(s): W G SKOGAN
• Date Published: 1974
• Length: 12 pages
• Corporate Author: University of Texas
• Publication Format: Document
• Publication Type: Survey
• Language: English
• Country: United States of America
• Note: REPRINT FROM SOCIAL SCIENCE QUARTERLY (JUNE 1974).

Annotation

THE AUTHOR SUGGESTS THAT WHILE OFFICIAL FIGURES DO NOT SPECIFY THE EXACT INCIDENCE OF CRIME IN A CITY, THEY DO INDICATE WITH SOME ACCURACY WHICH CITIES HAVE MORE CRIME THAN OTHERS.

Abstract

THIS REPORT HAS DRAWN UPON A SAMPLE SURVEY OF CITIZEN OPINIONS AND EXPERIENCES IN TEN MAJOR UNITED STATES CITIES (POPULATION OF BETWEEN 150,00 AND ONE MILLION IN 1970) FOR ESTIMATES OF THE INCIDENCE OF CRIMINAL VICTIMIZATION. OFFICIAL CITY CRIME STATISTICS IN TWO CATEGORIES - ROBBERY AND AUTO THEFT - ARE COMPARED WITH SURVEY-GENERATED MEASURES OF THE INCIDENCE OF VICTIMIZATION IN THE SAME COMMUNITIES. RESEARCHERS CONCLUDED THAT THE CONVERGENCE OF MEASURES INDICATES THAT QUANTITATIVE STUDIES OF INTER-CITY VARIATIONS IN OFFICIALLY MEASURED CRIME MAY NOT BE SERIOUSLY AFFECTED BY MEASUREMENT ERROR. THEY POINT OUT THAT STATISTICS, LIKE MEANS AND REGRESSION COEFFICIENTS (WHICH PURPORT TO REFLECT THE ACTUAL LEVELS OF MEASURED QUANTITIES) WILL BE INACCURATE, BUT CORRELATIONS AND SCATTERPLOTS CAN BE USED TO GOOD EFFECT IN ANALYZING THE CAUSES AND CONSEQUENCES OF VARIATIONS ACROSS JURISDICTIONS IN THE UNDERLYING, VICTIM-DEFINED DISTRIBUTION OF CRIME. (AUTHOR ABSTRACT MODIFIED)