The purpose of this article is to reduce potential statistical barriers and open doors to canonical correlation analysis (CCA) for applied behavioral scientists and personality researchers. CCA was selected for discussion, as it represents the highest level of the general linear model (GLM) and can be rather easily conceptualized as a method closely linked with the more widely understood Pearson r correlation coefficient. An understanding of CCA can lead to a more global appreciation of other univariate and multivariate methods in the GLM. We attempt to demonstrate CCA with basic language, using technical terminology only when necessary for understanding and use of the method. We present an entire example of a CCA analysis using SPSS (Version 11.0) with personality data.

This study examined 184 African-American outpatients in a mental health clinic in the inner city to define the rate of occurrence of traumatic experience and posttraumatic stress disorder (PTSD). This population experienced a high rate of severe trauma. Forty-three percent were found to have PTSD, as measured by the PTSD Symptom Scale. Finally, a chart review of 72 participants found that only 11 percent of participants who met DSM-IV criteria for PTSD also had a chart diagnosis of PTSD. PTSD is a common yet underrecognized and undertreated source of psychiatric morbidity in this urban community of African Americans with low socioeconomic status.

Psychotherapy has sometimes been seen as incongruent with religion and spirituality. This fact is even more pronounced when counseling lesbian, gay, and bisexual (LGB) clients, who feel as if their sexual orientation places them at odds with religious doctrine that is experienced as antigay. Postmodern theory provides a context for understanding socially constructed identities that may be in conflict with one another and may also provide some insight into how therapists may approach religious issues with LGB clients. The current study uses a mixed method design to investigate the relation between religious and sexuality variables in a sample of 422 LGB respondents. Quantitative results indicated that conservative religious beliefs were related to higher levels of shame, guilt, and internalized homophobia. Qualitative results appeared to highlight eight themes, the more dominant of which indicated that issues around sexual orientation were the catalyst for questioning or changing religious affiliation or beliefs.

Social science research often entails the comparison of two or more groups. For example, researchers may explore differences between sexes, races, ethnicities, sexual identities, treatment conditions, diagnostic categories, or various other grouping variables. While there are a number of ways to approach these comparisons, applied social science researchers often become comfortable with only one or two and may lack the time to learn or investigate others that may be more appropriate for their research questions. This article presents discriminant analysis as one of these alternative approaches. More specifically, it describes descriptive discriminant analysis in greater detail, including an example using SPSS (Version 11.0) output.

No abstract