Cohort-Size Sample-Size Conundrum: An Empirical Analysis and Assessment Using Homicide Arrest Data From 1960 to 1999

• NCJ Number: 200052
• Journal: Journal of Quantitative Criminology Volume: 19 Issue: 1 Dated: March 2003 Pages: 1-32
• Author(s): Robert M. O'Brien; Jean Stockard
• Date Published: March 2003
• Length: 32 pages
• Publication Format: Article
• Publication Type: Report (Study/Research)
• Language: English
• Country: United States of America

Annotation

This study addressed the sample-size problem in the birth-cohort assessment of the age distribution of homicide offending by applying a time-series-cross-section model (panel model) with age-period-specific homicide arrest data from the United States for each year from 1960 to 1999, while operationalizing cohorts as 5-year birth cohorts.

Abstract

A number of studies used the age-period-cohort characteristics (APCC) model to address the impact of cohort-related factors on the age distribution of homicide offending. Several of these studies used birth cohorts that span several years, an operationalization that most closely matches tenets of cohort theory; however, this approach significantly reduced the number of observations available for analysis. Other studies defined birth cohorts as those born within a single year, an operationalization that was theoretically problematic, but provided many more observations for analysis. The current study sought to move beyond these problems by using a multiyear conception of cohorts and data from single-year periods, thus retaining the theoretical advantage of a multiyear definition of cohorts while maintaining the statistical advantage of a larger sample size. Data were obtained on the number of homicide arrests by age from the Uniform Crime Reports for the years 1960 to 1999. Since 1960 these reports had presented data for homicide arrests by each year of age from 15 to 24 and for 5-year age groupings from 25-29 to 45-49. The panel model yielded results that were similar to those obtained from traditional multiyear APCC models. The results reinforced research that had shown the importance of relative cohort size and cohort variations in family structure in explaining variations in age-period-specific homicide rates. The additional observations provided by this study method allowed an examination of these relationships over time. The year-by-year estimates of the age distribution of homicide offending assisted in examining the model during the epidemic of youth homicides. 2 figures, 3 tables, and 53 references