Predicting Bidirectional Intimate Partner Violence: Demographic and Historical Factors That Influence Initiating Threats or Use of Violence by IPV Victims

Using data from the National Violence Against Women Survey, this study explored the role of gender and other demographic and historical factors that influence initiating threats or use of violence among a sample of intimate partner violence (IPV) victims—an element of bidirectional violence. For this study, involvement in a relationship marked by bidirectional violence was defined as an affirmative response to this question: Were you the first person to use/threaten physical force? after respondents self-identified as IPV victims. The hypothesized model to predict initiating threats or use of violence among male victims was not significant, but marital status, income, employment status, and childhood victimization experiences did significantly predict female behavior. Age, race, education, alcohol use, drug use, and posttraumatic stress disorder (PTSD) symptoms were not useful in explaining model variance for men or women. The rates of perpetration were equivalent for males and females; however, these findings suggest that gender is still an important context to consider when theorizing about bidirectional IPV.     

Model based clustering of large data sets: Tracing the development of spelling ability

There are two main theories with respect to the development of spelling ability: the stage model and the model of overlapping waves. In this paper exploratory model based clustering will be used to analyze the responses of more than 3500 pupils to subsets of 245 items. To evaluate the two theories, the resulting clusters will be ordered along a developmental dimension using an external criterion. Solutions for three statistical problems will be given: (1) an algorithm that can handle large data sets and only renders non-degenerate clusters; (2) a goodness of fit test that is not affected by the fact that the number of possible response vectors by far out-weights the number of observed response vectors; and (3) a new technique,data expunction, that can be used to evaluate goodness-of-fit tests if the missing data mechanism is known. Research supported by a grant (NWO 411-21-006) of the Dutch Organization for Scientific Research.