On the Use of Mixed Markov Models for Intensive Longitudinal Data.

Markov modeling presents an attractive analytical framework for researchers who are interested in state-switching processes occurring within a person, dyad, family, group, or other system over time. Markov modeling is flexible and can be used with various types of data to study observed or latent state-switching processes, and can include subject-specific random effects to account for heterogeneity. We focus on the application of mixed Markov models to intensive longitudinal data sets in psychology, which are becoming ever more common and provide a rich description of each subject's process. We examine how specifications of a Markov model change when continuous random effect distributions are included, and how mixed Markov models can be used in the intensive longitudinal research context. Advantages of Bayesian estimation are discussed and the approach is illustrated by two empirical applications.

Data analytic techniques for treatment outcome studies with pretest/posttest measurements: an extensive primer.

This paper discusses several data analytic technique, for examining treatment efficacy in pretest-posttest control group designs. The following approaches are described: ANOVA on post scores, ANOVA on difference scores, split-plot repeated measures ANOVA, profile analysis, and ANOCOVA with prescore as the co-variate. Guidelines for choosing between available techniques are provided; the primary focus here is on the nature of the null hypothesis, the assumptions underlying the approach, and the power of the procedure. The importance of examining the characteristics of the data set in selecting an analytic technique is illustrated.

Targeted prevention of unipolar depressive disorder in an at-risk sample of high school adolescents: a randomized trial of a group cognitive intervention.

OBJECTIVES: This investigation attempted to prevent unipolar depressive episodes in a sample of high school adolescents with an elevated risk of depressive disorder. METHOD: Adolescents at risk for future depressive disorder by virtue of having elevated depressive symptomatology were selected with a two-stage case-finding procedure. The Center for Epidemiologic Studies-Depression Scale (CES-D) was administered to 1,652 students; adolescents with elevated CES-D scores were interviewed with the Schedule for Affective Disorders and Schizophrenia for School-Age Children. Subjects with current affective diagnoses were referred to nonexperimental services. The remaining 150 consenting subjects were considered at risk for future depression and randomized to either a 15-session cognitive group prevention intervention or an "usual care" control condition. Subjects were reassessed for DSM-III-R diagnostic status after the intervention and at 6- and 12-month follow-up points. RESULTS: Survival analyses indicated a significant 12-month advantage for the prevention program, with affective disorder total incidence rates of 14.5% for the active intervention, versus 25.7% for the control condition. No differences were detected for nonaffective disorders across the study period. CONCLUSION: Depressive disorder can be successfully prevented among adolescents with an elevated future risk.

Applicability of the Impact on Family Scale for assessing families with behaviorally difficult children.

The present paper reports a series of studies on the potential usefulness of the Stein and Riessman Impact on Family Scale for assessing the effects of behaviorally difficult children on their families. Subjects were parents of 54 clinic and 76 nonclinic children who completed a child behavior or child temperament questionnaire in addition to the Impact on Family Scale. Findings suggest that, while the scale was developed for assessing the influence of a physically ill child on the family, this general assessment approach may also have value in assessing family-related changes associated with having a child who is difficult to look after.

Child temperament, maternal adjustment, and changes in family life style.

Child temperament has been implicated as a relevant factor in understanding parental adjustment. In a study of 77 mothers of 3- and 4-year-old children, difficult child temperament was found to be directly related to maternal distress, discomfort in the role of parent, poor spousal relationships, and negative changes in way of life. Quality and intensity of the child's mood were most predictive of these difficulties.