NCJ Number
91773
Date Published
1983
Length
74 pages
Annotation
Studies of discrimination in case disposition suffer from at least one of three major shortcomings: absence of formal models of processing decisions in the criminal justice system, sample selection biases resulting from screening and processing decisions, and use of arbitrary scales to measure qualitatively different dispositions.
Abstract
In suggesting ways to cope with these problems, the authors first review statistical issues that arise in analyzing binary data, sample selection phenomenon, and procedures to deal with selection bias at different processing stages. They develop a model of the criminal justice system which characterizes the interrelationships of four aspects of case processing: the decision to prosecute, plea bargaining, trial, and sentencing. This model implies that stages in the criminal justice system cannot be neatly separated, that sentence in a negotiated plea will be a function of the interaction of the seriousness of the offense and case quality, and that an analysis of the determinants of conviction should not mix guilty pleas and trial convictions. The paper reviews nine studies in the context of the sample selection phenomenon and this model. Generally, selection bias is likely to cause all studies to underestimate the magnitude of discrimination in sentencing decisions. In addition, mixing guilty pleas and trial convictions blurs the relationship between sentence and offense seriousness and defendant's characteristics, making assessment of discrimination difficult. The paper also discusses alternative models of sentencing that do not require the use of arbitrary sentencing indexes and experimental approaches to measuring discrimination. Tables, equations, and 29 references are included.