Register  |  Login
Xin M. TU Dr. Tu is Professor and Co-Director of the Division of Psychiatric Statistics (DPS), which focuses on collaborations with investigators in psychosocial research within the UR Medical Center. He is also the Director of the Biostatistics Consulting Service Center and Associate Chair for Consulting, Collaboration and Research of the Department of Biostatistics and Computational Biology. With over 20 years of experience in biostatistical and psychosocial research and over 150 publications, Dr. Tu is well versed in longitudinal data analysis, SEM, counterfactual outcome based causal models, distribution-free models, latent growth mixture models, functional response models, and their applications to observational studies and randomized controlled trials across a range of disciplines, especially in the behavioral and social sciences. Dr. Tu‘s co-authored `Modern Applied U-statistics’ book focuses on the theory and application of U-statistics and functional response models, the latter being a generalization of regression to the context of complex endogenous relationships defined by multiple subjects’, which provides the premise for modeling social network data, mediation relationships, population mixtures and counterfactual outcomes. Dr. Tu is also an experienced educator. His recent co-authored book entitled `Applied Categorical and Count Data Analysis’ is filled with real study data in psychosocial research and blended with classic concepts such as instrumentation and agreement analysis and modern topics such as causal inference and longitudinal data, all topped off with a detailed documentation of sample programming codes for model implementations, including support for SAS, SPSS, and STATA. Also, in a recently published volume in `Modern Clinical Trial Analysis’ he co-edited for edited for the Springer's Applied Bioinformatics and Biostatistics in Cancer Research book series, he dedicated a large portion of the volume to contemporary topics such quality of life and cost effectiveness analysis in cancer research to complement a research field traditionally dominated by survival analysis.