Parametrizing Age, Period, and Cohort Effects: An Application to U.S. Delinquency Rates, 1964-1973

The simultaneous existence of age, period, & cohort effects in a population over time can be understood in terms of the simultaneous existence of row, column, & diagonal effects in a table. An approach to the parameterization of these various effects is described, based on multiplicative mod...

Full description

Saved in:
Bibliographic Details
Published in:Sociological methodology 1978-01, Vol.9, p.116-140
Main Author: Pullum, Thomas W.
Format: Article
Language:English
Subjects:
Age/Ageism
Ambiguity
Arrest rates
Cohort effect
Cohort/Cohorts
Data models
Degrees of freedom
Delinquency
Effect/Effects/Effectiveness
Estimation methods
Modeling
Parameter/Parameters/ Parameteric/ Parametrical
Parametric models
Period/Periods/Periodicity
Rate/Rates
Ratios
Regression coefficients
United States/US
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The simultaneous existence of age, period, & cohort effects in a population over time can be understood in terms of the simultaneous existence of row, column, & diagonal effects in a table. An approach to the parameterization of these various effects is described, based on multiplicative models. This approach is applied to arrest rates in the US for ages 15-24 over the years 1964-1973, illustrating the uses of 1-, 2-, & 3-factor models. The problem of choosing an optimal parameterization is explored. It is shown that 2-way analyses can be synthesized into a 3-way age/period/cohort analysis with the same scale properties. 6 Tables. W. H. Stoddard.
ISSN:0081-1750
1467-9531
DOI:10.2307/270806