The models incorporate two features. First, victimizations for given housing units are dependent over time, while those from housing unit to housing unit can be independent (conditional on the parameters of the model). Second, there is an explicit way of using victimization information on a given housing unit to help impute missing observations for that housing unit. The first of these goals was met by introducing a beta-binomial model for the number of months in which a given housing unit is victimized. The second goal, however, has not yet been successfully met within the framework of the beta-binomial model. Two references are listed.
Downloads
Similar Publications
- Examining Equity in State Victim Compensation Programs: A Multilevel Analysis
- The Effects of Risky Behaviors and Social Factors on the Frequency of Fraud Victimization Among Known Victims
- Reducing Disorder, Fear, and Crime in Public Housing: An Evaluation of a Drug Crime Elimination Program in Spokane, Washington: Final Report