Strategies for eliciting and merging confidential social research data

This report presents, discusses and extends strategic models for representing the process of merging records from different sources when confidentiality of the records is required by law or custom. Examples and variations on the models cover simple situations, such as eliciting anonymous data from previously identified respondents, as well as more complex merge operations, such as merging files from different data archives and merging data under code linkage systems. The versatility and potential corruptibility of the models are also discussed.Supported by NSF Grants GI29843 and GS320-73X. Professors Eli Rubenstein, Donald T. Campbell, and Lance Hoffman were generous in providing advice on earlier drafts of the paper. However, views expressed here do not necessarily reflect the views of the sponsoring agency or of these individuals.     

On the Robustness and Validity of Groups

In response to Nagin's comment on our paper, Methodological Sensitivities to Latent Class Analysis of Long-Term Criminal Trajectories, we reconsider the robustness and validity of group-based approaches to criminal trajectories and introduce additional issues for future research. We emphasize the limitations of typological approaches and the dangers of reifying the idea of distinct offender groupings for research and policy. We also clarify misunderstandings about the use of hierarchical linear models for studying trajectories of crime. Our basic conclusion is that methods in criminology need to be more tightly linked with theory.     

A re-examination of the MMPI-2 aggressiveness and immaturity indices in law enforcement screening

This study reports an analysis of Bartol's (1991) Immaturity Index and Hargrave and associates' (1988) Aggressiveness Index as a measure of police conduct. The correlations between the supervisory ratings and the Immaturity and Aggressiveness indices were examined for 1020 law enforcement officers. The results showed that Immaturity Index was related to termination for failure to complete training and insubordination. The Aggressiveness Index was related to a termination for failure to complete training and several other problematic police behaviors, but was not found to be specifically linked with acts of aggression. Implications for using these two indices in law enforcement selection are discussed. Authors' Note: Cary Rostow, Ph.D. is president of Matrix, Inc., Baton Rouge, Louisiana, and is in private practice in Baton Rouge. Robert Davis, Ph.D., is executive vice-president and director of science, research, and development for Matrix, Inc., and has a private practice in Baton Rouge. James B. Pinston, Ph.D., is a clinical neuropsychologist within the department of neurology at the Louisiana State University Health Sciences Center and School of Medicine in Shreveport, Louisiana. Dennis R. Combs, Ph.D., is an assistant professor of psychology at the University of Tulsa. Dennis R. Dixon, M.A., is currently a doctoral student at Louisiana State University.     

Applying a forensic actuarial assessment (the Violence Risk Appraisal Guide) to nonforensic patients

The actuarial Violence Risk Appraisal Guide (VRAG) was developed for male offenders where it has shown excellent replicability in many new forensic samples using officially recorded outcomes. Clinicians also make decisions, however, about the risk of interpersonal violence posed by nonforensic psychiatric patients of both sexes. Could an actuarial risk assessment developed for male forensic populations be used for a broader clientele? We modified the VRAG to permit evaluation using data from the MacArthur Violence Risk Assessment Study that included nonforensic male and female patients and primarily self-reported violence. The modified VRAG yielded a large effect size in the prediction of dichotomous postdischarge severe violence over 20 and 50 weeks. Accuracy of VRAG predictions was unrelated to sex. The results provide evidence about the robustness of comprehensive actuarial risk assessments and the generality of the personal factors that underlie violent behavior.     

A comparison of nonviolent, psychologically violent, and physically violent male college daters

This brief report explores dating violence by comparing three groups of male college students (nonabusive, psychologically abusive only, and physically abusive). These men were compared on measures of impulsivity, problems with alcohol, life satisfaction, anger management skills, history of witnessing abuse, history of experiencing abuse, and relationship satisfaction. Data for this analysis were obtained from a sample of 115 male college students. Differences between the three groups of men were found in the levels of problems with alcohol, relationship satisfaction, and anger management skills. Anger management skills best differentiated the three groups of men leading to the conclusion that dating violence prevention and intervention strategies with male college students should address anger management skills.