Title: Multivariate shared parameter mixed-effects location scale (MELS) models for intensive longitudinal data
Authors: Donald Hedeker - University of Chicago (United States) [presenting]
Abstract: Intensive longitudinal data using Ecological Momentary Assessment (EMA) are obtained to study subjective experiences within changing environmental contexts. The intensive longitudinal data allow one to characterize a subject's mean and variance and specify models for both. We focus on an EMA study of dual users (i.e., both combustible and electronic cigarette users), where interest is on characterizing mood associated with these nicotine products, and whether the subject's mood response relates to future nicotine product use. For this, the MELS model of the EMA data includes random subject effects for the mean (i.e., location), which characterize the subject's differential mood response to combustible and electronic cigarettes. A random effect for the subject's variability (i.e., scale) is also included to characterize the subject's mood consistency/erraticism. These random location and scale effects are then shared in a bivariate longitudinal mixed model of post-EMA nicotine product use (both combustible and electronic cigarettes).