Variable Assessment in Latent Class Models.

The latent class model provides an important platform for jointly modeling mixed-mode data - i.e., discrete and continuous data with various parametric distributions. Multiple mixed-mode variables are used to cluster subjects into latent classes. While the mixed-mode latent class analysis is a powerful tool for statisticians, few studies are focused on assessing the contribution of mixed-mode variables in discriminating latent classes. Novel measures are derived for assessing both absolute and relative impacts of mixed-mode variables in latent class analysis. Specifically, the expected posterior gradient and the Kolmogorov variation of the posterior distribution, as well as related properties are studied. Numerical results are presented to illustrate the measures.

Multi-profile hidden Markov model for mood, dietary intake, and physical activity in an intervention study of childhood obesity.

Motivated by an application to childhood obesity data in a clinical trial, this paper describes a multi-profile hidden Markov model (HMM) that uses several temporal chains of measures respectively related to psychosocial attributes, dietary intake, and energy expenditure behaviors of adolescents in a school setting. Using these psychological and behavioral profiles, the model delineates health states from the longitudinal data set. Furthermore, a two-level regression model that takes into account the clustering effects of students within school is used to assess the effects of school-based and community-based interventions and other risk factors on the transition between health states over time. The results from our study suggest that female students tend to decrease their physical activities despite a high level of anxiety about weight. The finding is consistent across intervention and control arms.

Dysregulation of DGCR6 and DGCR6L: psychopathological outcomes in chromosome 22q11.2 deletion syndrome.

Chromosome 22q11.2 deletion syndrome (22q11DS) is the most common microdeletion syndrome in humans. It is typified by highly variable symptoms, which might be explained by epigenetic regulation of genes in the interval. Using computational algorithms, our laboratory previously predicted that DiGeorge critical region 6 (DGCR6), which lies within the deletion interval, is imprinted in humans. Expression and epigenetic regulation of this gene have not, however, been examined in 22q11DS subjects. The purpose of this study was to determine if the expression levels of DGCR6 and its duplicate copy DGCR6L in 22q11DS subjects are associated with the parent-of-origin of the deletion and childhood psychopathologies. Our investigation showed no evidence of parent-of-origin-related differences in expression of both DGCR6 and DGCR6L. However, we found that the variability in DGCR6 expression was significantly greater in 22q11DS children than in age and gender-matched control individuals. Children with 22q11DS who had anxiety disorders had significantly lower DGCR6 expression, especially in subjects with the deletion on the maternal chromosome, despite the lack of imprinting. Our findings indicate that epigenetic mechanisms other than imprinting contribute to the dysregulation of these genes and the associated childhood psychopathologies observed in individuals with 22q11DS. Further studies are now needed to test the usefulness of DGCR6 and DGCR6L expression and alterations in the epigenome at these loci in predicting childhood anxiety and associated adult-onset pathologies in 22q11DS subjects.