Identifying subgroups that succeed or fail with three levels of physical activity intervention: the Activity Counseling Trial.

The authors used recursive partitioning methods to identify combinations of baseline characteristics that predict 2-year physical activity success in each of 3 physical activity interventions delivered in the multisite Activity Counseling Trial. The sample consisted of 874 initially sedentary primary care patients, ages 35-75 years, who were at risk for cardiovascular disease. Predictors of 2-year success were specific to each intervention and represented a range of domains, including physiological, demographic, psychosocial, health-related, and environmental variables. The results indicate how specific patient subgroups (e.g., obese, unfit individuals; high-income individuals in stable health) may respond differently to varying levels and amounts of professional assistance and support. The methods used provide a practical first step toward identifying clinically meaningful patient subgroups for further systematic investigation.     

Perceptual Categorization: Connectionist Modelling and Decision Rules

Although it is currently popular to model human associative learning using connectionist networks, the mechanism by which their output activations are converted to probabilities of response has received relatively little attention. Several possible models of this decision process are considered here, including a simple ratio rule, a simple difference rule, their exponential versions, and a winner-take-all network. Two categorization experiments that attempt to dissociate these models are reported. Analogues of the experiments were presented to a single-layer, feed-forward, delta-rule network. Only the exponential ratio rule and the winner-take-all architecture, acting on the networks' output activations that corresponded to responses available on test, were capable of fully predicting the mean response results. In addition, unlike the exponential ratio rule, the winner-take-all model has the potential to predict latencies. Further studies will be required to determine whether latencies produced under more stringent conditions conform to the model's predictions.