Rehabilitation Issues, Problems, and Prospects in Boot Camp by Benda Brent;Pallone Nathaniel J.;

Author:Benda, Brent;Pallone, Nathaniel J.;
Language: eng
Format: epub
Publisher: Taylor & Francis Group

Cox’s Proportional Hazards Models

Cox’s proportional hazards models are conducted in the complete sample, using statistical interactions to examine gender differences, because of the relative small number of women available at the time of the study. The first Cox’s proportional hazards model (Table 2) is a hierarchical analysis, where hypothesized ameliorating experiences are added in the second hierarchy to predictors considered in the first hierarchy. In Cox regression, the baseline hazard rate (HR) describes the risk of when the event (i.e., felony arrest or parole violation) will occur. A value greater than 1 reflects a greater hazard rate of recidivism (i.e., felony arrest or parole violation) for each unit of change in the predictor variable, and a beta value less than 1 reflects a smaller hazard rate of recidivism at each unit of change in the predictor variable. Continuous data are standardized to normalize distributions and to make coefficients more meaningful. The estimated betas give the magnitude of effect of each predictor on the log odds (logit) of the hazard of recidivism. Taking antilogs (exponents) of the estimated betas converts the effects to the odds of the hazard of recidivism. For example, the effect of age on recidivism is .25 (Table 2), which when exponentiated indicated that the odds of the hazard of recidivism decreases by .76 for each unit (i.e., one standard deviation) increase in age, which is a 24 percent decrease (1 .76 = .24).

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.