Causal effect modeling with naturalistic rather than experimental data is challenging. In observational studies participants in different treatment conditions may also differ on pretreatment characteristics that influence outcomes. Propensity score methods can theoretically eliminate these confounds for all observed covariates, but accurate estimation of propensity scores is impeded by large numbers of covariates, uncertain functional forms for their associations with treatment selection, and other problems. This article demonstrates that boosting, a modern statistical technique, can overcome many of these obstacles. The authors illustrate this approach with a study of adolescent probationers in substance abuse treatment programs. Propensity score weights estimated using boosting eliminate most pretreatment group differences and substantially alter the apparent relative effects of adolescent substance abuse treatment.

This study examined 2 process variables, emotional engagement and habituation, and outcome of exposure therapy for posttraumatic stress disorder. Thirty-seven female assault victims received treatment that involved repeated imaginal reliving of their trauma, and rated their distress at 10-min intervals. The average distress levels during each of 6 exposure sessions were submitted to a cluster analysis. Three distinct groups of clients with different patterns of distress were found: high initial engagement and gradual habituation between sessions, high initial engagement without habituation, and moderate initial engagement without habituation. Clients with the 1st distress pattern improved more in treatment than the other clients. The results are discussed within the framework of emotional processing theory, emphasizing the crucial role of emotional engagement and habituation in exposure therapy.

No abstract

No abstract

No abstract