Finite Mixtures for Simultaneously Modelling Differential Effects and Non-Normal Distributions.

Regression mixture models have been increasingly applied in the social and behavioral sciences as a method for identifying differential effects of predictors on outcomes. While the typical specification of this approach is sensitive to violations of distributional assumptions, alternative methods for capturing the number of differential effects have been shown to be robust. Yet, there is still a need to better describe differential effects that exist when using regression mixture models. The current study tests a new approach that uses sets of classes (called differential effects sets) to simultaneously model differential effects and account for non-normal error distributions. Monte Carlo simulations are used to examine the performance of the approach. The number of classes needed to represent departures from normality is shown to be dependent on the degree of skew. The use of differential effects sets reduced bias in parameter estimates. Applied analyses demonstrated the implementation of the approach for describing differential effects of parental health problems on adolescent body mass index using differential effects sets approach. Findings support the usefulness of the approach which overcomes the limitations of previous approaches for handling non-normal errors.

A multilevel approach to examining time-specific effects in accelerometer-assessed physical activity.

OBJECTIVES: Popular methods for analyzing accelerometer data often use a single physical activity outcome variable such as average-weekly or total physical activity. These approaches limit the types of research questions that can be answered and fail to utilize the detailed, time-specific information available from accelerometers. This study proposes the use of multilevel modeling, which tested intervention effects at specific time periods. DESIGN: The motivating example was the Active by Choice Today trial. Simulations were used to test whether the application of time-specific hypotheses about when physical activity intervention treatment effects were expected to occur (e.g., after-school hours) increased power to detect effects compared to traditional methods. METHODS: Six simulation conditions were tested: (1) no treatment effects (to test the type 1 error rate), (2) time-specific effects, but no traditionally-tested effects, (3) traditionally-tested effects, but no time-specific effects, and (4) combinations of traditional and time-specific effects in 3 proportions. RESULTS: Results showed the proposed multilevel approach demonstrated appropriate type 1 error rates and increased power to detect treatment effects during hypothesized times by 31-38 percentage points compared to traditional approaches. This was consistent across varying proportions of traditional versus time-specific effects, and there was no loss of power using the multilevel approach when only traditional effects were present. CONCLUSIONS: The current study showed potential advantages of testing time-specific hypotheses about intervention effects using a multilevel time-specific approach. This approach may show intervention effects when traditional approaches do not. Future research should explore the application of this additional analytic tool for accelerometer physical activity estimates.