Methods for Studying Variability as a Predictor of Health Status

Means or other central tendency measures are by far the most common focus of statistical analyses. However, as Carroll (2003) noted, ``systematic dependence of variability on known factors'' may be ``fundamental to the proper solution of scientific problems'' in certain settings. Hence we develop a latent cluster model that relates underlying ``clusters'' of variability to baseline or outcome measures of interest, and apply the method to relating psychological affect data to depression in recovering MI patients. We discuss extending these methods to incorporate latent cluster models that jointly cluster variance structures with mean structures such as mean longitudinal profile to more fully describe the information available in longitudinal datasets, and propose methods to jointly model short-term and long-term variance in continuous longitudinal data.