Dr. Jianhua Hu
The University of Texas MD Anderson Cancer Center
Department of Biostatistics
- Modeling correlated/longitudinal data
- Analysis of high dimensional bioinformatics/biomedical data
- Dimension reduction
- Variable selection
- Robust and nonparametric statistics
- Bayesian statistics
- Clinical trial designs
As a statistician with interests in theory, methodology, and applications in biology as well as bioinformatics data and clinical trial design, my research is interdisciplinary. My research areas cover both applied and theoretical statistics. The applications include high dimensional genomics and proteomics data, network construction, longitudinal and spatial data, genetic and environmental epidemiology. Statistical methodologies and theory focus on variable selection, dimension reduction, modeling of longitudinal and spatial data, robust statistics, non- and semiparametric modeling, adaptive clinical trial designs, and Bayesian statistics.
Projects/Techniques: An example is likelihood based dimension reduction method for binary data, such as principal component analysis. It requires a Ph.D. student to have knowledge of maximum likelihood estimation, EM algorithm, and principal component analysis. Programming in R (or Matlab, C) language is required.
Feng X, He X, Hu J. Wild bootstrap for quantile regression. Biometrika 98:995-999, 2011.
Maadooliat M, Huang J, Hu J. Analyzing multiple-probe microarray: estimation and application of gene expression indexes. Biometrics 68:784-792, 2012.
Li B, Liang F, Hu J, He X. Reno: Regularized Nonparametric Analysis of Protein Lysate Array Data. Bioinformatics 28:1223-1229, 2012.
Hu J, He X. Searching for Alternative Splicing with a Joint Model on Probe Measurability and Expression Intensities. Journal of the American Statistical Association. In Press.