A Factor Mixture Model Approach to Elaborating on Offender Mental Health Classification With the MMPI–2–RF

Abstract

A large proportion of prison inmates suffer from mental illnesses or severe personality disorders; therefore, offender classification is a worthwhile endeavor both for efficiently allocating mental health treatment resources and security risk classification. This study sought to elaborate on offender classification by using an advanced statistical technique, factor mixture modeling, which capitalizes on the strengths of both latent trait analysis and latent class analysis. A sample consisting of 616 male and 194 female prison inmates was used for this purpose. The MMPI–2–RF Restructured Clinical (RC) scales were used to elaborate on a variety of latent trait, latent class, and factor mixture models. A 3-factor, 5-class mixture model was deemed optimal in this sample. Remaining MMPI–2–RF scales as well as scores on external criterion measures relevant to externalizing psychopathology were used to further elaborate on the utility of the resulting latent classes. These analyses indicated that 3 of the 5 classes were predominantly different expressions of externalizing personality proclivities, whereas the remaining 2 indicated inmates with substantial internalizing or thought-disordered characteristics. Implications of these findings are discussed.

Acknowledgments

I am grateful to Yossef Ben-Porath and Auke Tellegen for their consultation on several conceptual aspects of this article, as well as to Michael Hallquist and Aidan Wright for statistical consultation. I also thank Tasha Phillips for giving me permission to use the female Ohio Department of Rehabilitation and Correction data. Finally, I thank Yossef Ben-Porath, Diane Gartland, and the Michigan Department of Correction for facilitating the original data collection of the male offender sample.

Notes

The default Mplus rotation method (Geomin) was initially used, but it generated out-of-bounds parameters, which is sometimes a limitation of this method. CF–Equamax is an alternative method that has been shown to perform well (Sass & Schmidt, 2010), and yielded a solution consistent with conceptual expectations and was therefore retained. Analyses based on other rotation methods can be made available on request.

One could also make an argument for the 12-class model given the 9-point increase in BIC with the 13-class model, but given that this clearly was not a consistent trend, the results (with respect to BIC) favor the 14-class model, especially because the latter model had a substantially lower BIC value (ΔBIC = 12) compared to the 12-class model.

These are available on request.

As mentioned in the Method section, although race and ethnicity would have been an important variable, it was not systematically coded for the male offenders.