Division faculty members conduct independent methodological research into innovative methods to design and analyze research studies. Our collaborative research drives statistical methodological research and innovative statistical methods benefit the scientific investigations. The division has a strong publication record in multiple areas of methodological research in biostatistics and bioinformatics. A sample is provided below.
-
Design and analysis of clinical trials and translational studies. The adaptive clinical trial designs developed by the faculty provide an innovative approach for personalized therapy. In addition, a novel experimental design and analysis method for drug combinations is developed by integrating concepts in modern statistics and pharmacology; and more fundamental research in experimental design provides a way to make laboratory research more efficient (see publications of Drs. Tan, Fang and Chen).
-
Statistical bioinformatics applies statistical and computational methods or tools in analyzing high dimensional data, such as gene expression microarrays, single nucleotide polymorphism (SNP) analyses, integrated genomic data, next generation sequencing, proteomics, and imaging data. Faculty members at the Division are at the forefront of developing statistical bioinformatics methodology (see publications of Drs. Liu, Tan and Fang).
-
Evaluation of biomarkers and predictive modeling are the strength and interest of many faculty members at the division (see publications of Drs. Liu, Magder, Shardell and Tan).
-
Statistical methods for comparative effectiveness research involve multi-level/hierarchical models, causal inference and Bayesian models where the division faculty is at the forefront of the development (see publications of Drs. Brown, Fang, Liu, Magder, Shardell, and Tan).
-
It remains to be a challenge to compare two treatments when the observed data are interval-censored or panel-count data, which often occurs during clinical trials and follow-up studies. Faculty have developed statistical methods for such data (see publications of Dr. Fang, Zhan)
-
Incomplete data (i.e., missing, censored, or coarsened data) pose a unique problem in population research: it may lead to selection bias; however, the bias cannot be quantified by the observed data. Division faculty has been actively developing statistical methods that address this issue (see publications of Dr. Shardell). Recently, methods for missing data problems using Bayesian approach are summarized in a book (see publications of Drs. Tan and Tian).