Keynote and Featured Speakers
Keynote: Fifty years of SEM: Some reflections in the black mirror
Keynote: Modeling between and within-subject variances using mixed effects location scale models for intensive longitudinal data
Intensive longitudinal data are increasingly encountered in many research areas. For example, ecological momentary assessment and/or experience sampling methods are often used to study subjective experiences within changing environmental contexts. In these studies, up to 30 or 40 observations are usually obtained for each subject over a period of a week or so. Because there are so many measurements per subject, one can characterize a subject’s mean and variance and can specify models for both. In this presentation, we focus on an adolescent smoking study using ecological momentary assessment where interest is on characterizing changes in mood variation. We describe how covariates can influence the mood variances and also extend the statistical model by adding a subject-level random effect to the within-subject variance specification. This permits subjects to have influence on the mean, or location, and variability, or (square of the) scale, of their mood responses. Models for both continuous and ordinal outcomes are described and will be illustrated with examples. These mixed-effects location scale models have useful applications in many research areas where interest centers on the joint modeling of the mean and variance structure.
Keynote: Bigger data and stronger causal inference from quasi-experiments
This presentation summarizes an ongoing line of work in which estimates from an experiment are compared to various quasi-experimental design and analytic practices where the treatment group is shared with the experiment but the way of forming the non-equivalent group obviously is not. Work of this kind on regression discontinuity (RD) and comparative RD is summarized in terms of bias reduction and precision both at and away from the RD cutoff. Also summarized is work on interrupted time series (ITS) designs and comparative ITS designs. But most attention is paid to simpler non-equivalent control group designs to illustrate practices in this area that reproduce experimental estimates. Included here is work on various ways of selecting intact but non-equivalent comparison groups and work on various ways of selecting covariates to control for any selection that remains after non-equivalent comparison groups have been chosen.