| Biography | |
|---|---|
 Dr. Depeng Jiang University of Manitoba, Canada |
|
| Title: Random Intercept Latent Transition Analysis for Program Evaluation with Multilevel and Multivariate Longitudinal Data | |
| Abstract: Many intervention programs often have multiple outcome variables, each being reported for multiple time points (e.g., pre and post intervention) where data for participants are organized at more than one level (students nested in schools). The latent transition analysis (LTA) is a well-known approach for modeling transition over time. In this paper, we propose to use the LTA with random intercepts for program evaluation with multilevel and multivariate longitudinal data. Between-subject variation is separated from the within-subject latent class transition over time allowing a clear interpretation of the data. The robust standard errors in LTA were considered to consider the non-independence of observations due to the clustered or multilevel structure. We conduct both simulation studies and application to real prevention programs to compare the LTA models with different random intercept variations with the regular LTA. The strengths and limitations of these LTA models are discussed. | |
| Biography: Dr. Depeng Jiang is an Associate Professor in the Department of Community Health Sciences of University of Manitoba and presently serving as a Lead of Biostatistical Group within George & Fay Yee Centre for Healthcare Innovation. Dr. Jiang had many years of experience in providing statistical consulting to a broad range of clients and training students and researchers on the conduct of statistical analyses. His main research interests include longitudinal analysis and multilevel models, person-centered statistical approaches (latent class analysis and growth mixture models), structural equation models, clinical trial design and mental health program evaluation. He has made significant contribution to advanced statistical methods and models for complex data and multilevel research. He has consolidated and made available his program of research to local, national, and international venues, while providing training on advanced statistical methods for students, researchers and faculty members from multidisciplinary area. Application of these methods has not only provided the necessary evidence to support decision making, but also significantly increase researchers and trainees’ chances of success in journal publications and grant competition, as well as transformed their abilities to do research. | |
