The pre-conference workshop on “Modeling Intensive Longitudinal Data with Mixed-Effects Location Scale (MELS) Models” on April 13 is taught by our keynote speaker Prof. dr. Donald Hedeker – University of Chicago.

Intensive longitudinal data are increasingly encountered in many research areas. For example, ecological momentary assessment (EMA), experience sampling method (ESM), and/or mobile health (mHealth) methods are often used to study subjective experiences within changing environmental contexts. In these studies, large numbers of observations are usually obtained for each subject over periods of days, weeks, months, etc. Such intensive longitudinal data allow one to characterize and model not just the mean response, but also between-subjects (BS) and within-subjects (WS) variances, both at the population and subject levels. This extension, termed the mixed-effects location scale (MELS) model, extends multilevel model which typically assume that these variances are constant across subjects.

Software for the MELS model has been developed, including the R package MixLS and the standalone program MixWILD. The latter includes a graphical-user interface (GUI) to facilitate its use. MixWILD also allows the random effects from the MELS model (of the ESM data) to be used as predictors in a second stage model, for example to predict a future outcome beyond the ESM data collection period. In this workshop, usage of these programs will be described and illustrated using worked examples.

More details on required preparation and availability of software syntax and data will follow later.

The workshop session runs from 9:00 till 16:00. Coffee/tea and lunch are included.

Note that you can also register for this workshop without participating in the conference.