The Statistics Department is constantly expanding its role as a vibrant and internationally recognized center of research excellence in high-dimensional statistics, biostatistics and bioinformatics, theory based methodological research, and Bayesian methods through the work of faculty, and by establishing cross-disciplinary collaborations within the Fox School and across Temple University. The Statistics department is increasing the amount of funds awarded from research grants to expand on these endeavors.
The statistical innovations made in the research offer significant advances to the core of statistics and impacts numerous other scientific disciplines. Faculty publish articles in top statistics journals, are highly sought after speakers, mentor graduate students who produce award-winning statistical research, and receive external funding from agencies such as the National Science Foundation and the National Institutes of Health. These statistical innovations are applied to complex scientific problems in diverse fields such as medicine, marketing, ecology, computer science and criminal justice to provide solutions to crucial questions and improve the societal health and well-being.
Themes – The Global Impact of Fox School Research
Research is a top priority at the Fox School. Faculty and students across departments regularly make unique contributions that impact the academic world and the global business community, as well as society as a whole. Learn more about the important work done at Fox by exploring the following research themes.
The study of high-dimensional statistics has emerged in recent years as a new field due to the confluence of recent advances in statistics and the ready availability of fast, efficient, and cheap computing. The field of statistics has responded to the urgent need for the development of newer and more appropriate statistical tools to analyze high-dimensional problems involving Big Data. It encompasses several emerging fields, such as high-dimensional statistical inference, dimensionality reduction, data mining, machine learning, and bioinformatics. In fact, many of these and other emerging statistical topics are modernized versions of traditional statistical areas such as multivariate analysis, Bayesian analysis, time series analysis, biostatistics, and statistical computing and graphics
The Department continues advancing its knowledge and reputation in theoretical, computational, and applied research. Today, the quality and relevance of statistical research is primarily determined by modern applications involving high-dimensional data. Our department enjoys excellence in research in biostatistics, which is closely related to bioinformatics. Preserving that reputation is one of our main research goals. Moreover, one of the objectives of the newly created Center for High-Dimensional Statistics is to foster and engage in cross-disciplinary research collaborations in the domain of Big Data. This includes interdisciplinary and collaborative research work within the Fox School involving other academic departments and research centers, working with the Biostatistics and Bioinformatics group at the Fox Chase Cancer Center, and collaborating with Temple University’s Center for Data Analytics and Biomedical Informatics.
Bayesian methods have become even more important today because of new computational breakthroughs. Members of the Statistics Department are developing and applying Bayesian Methods for the statistical analyses of high-dimensional data that arise from research in disciplines such as business, computer science, biology, and medicine.
Application-driven research focused on developing novel statistical methods or tools with solid theoretical foundation.
Institutes & Centers
The Biostatistics Research Center promotes research within the Department of Statistics to encourage professional activities within the Greater Philadelphia area. To advance this mission, the Center organizes and sponsors annual conferences and advanced short courses. It also helps students with summer fellowships, tuition support, and the presentation of papers at professional meetings. The Center additionally sponsors the Department of Statistics’ alumnae seminar series, cooperates with Temple Medical School faculty on research projects, and helps the Department of Statistics through the purchase of books for its Reading Room, and hardware and software for the Department’s computing facility.
High-Dimensional Statistics has emerged as a new field as a result of the confluence of recent advances made in Statistical Science in response to the urgent need for the development of newer and more appropriate Statistical Data Science tools to analyze data with high dimensions. The center engages the shared research interests and expertise of the Department of Statistical Science faculty to create an integrated and more vibrant place for research in a field of Statistical Science that is critically important in Data Science research. The center exploits its strategic advantage to develop and expand school and university-wide collaborative Data Science research opportunities and leverages research funding from government agencies and industries.
The Center for Statistical Analysis provides professional statistical consulting support and training to Temple faculty and researchers, as well as external clients in the business, industry, and government sectors. The Center provides assistance on the design of experiments and surveys, statistical analysis of data, interpretation of analysis, as well as advice on appropriate software. The Center accomplishes its objectives by providing statistical support to researchers and Centers within Temple, collaborating on interdisciplinary grant proposals, designing studies and data analysis projects for external clients in business and government, and organizing workshops and conferences.
Lin Q., Zhao Z., and Liu JS., (2018) On consistency and sparsity for sliced inverse regression in high dimensions. Annals of Statistics, 2, 580-610.
Franks AM., Markowetz F., and Airoldi EM., (2018) Refining cellular pathway models using an ensemble of heterogeneous data sources. Annals of Applied Statistics, 3, 1361-1384.
Yuan M., Tang CY., Hong Y., and Yang J., (2018) Disentangling and assessing uncertainties in multiperiod corporate default risk predictions. Annals of Applied Statistics, 4, 2587-2617.
Rubin, Donald B. B, (2017) Conditions for Ignoring the Missing-Data Mechanism in Likelihood Inferences for Parameter Subsets. Journal of the American Statistical Association, 517, 314-320.
Airoldi, Edoardo, (2017) Geometric Representations of Random Hypergraphs. Journal of the American Statistical Association, 517, 363-383.
Airoldi, Edoardo, (2017) Asymptotic and finite-sample properties of estimators based on stochastic gradients.Annals of Statistics, 4, 1694-1727.
Fan J., and Han X., (2017) Estimation of the false discovery proportion with unknown dependence. Journal of the Royal Statistical Society. Series B: Statistical Methodology, 4, 1143-1164.
Yu, Z., Dong, Y. and Zhu, L. X. (2016) Trace Pursuit: A General Framework for Model-Free Variable Selection. Journal of the American Statistical Association, 111, 813-821.
Yu, Z., Dong, Y. and Shao, J. (2016) On Marginal Sliced Inverse Regression for Ultrahigh Dimensional Model Free Feature Selection. Annals of Statistics, 44, 2594-2623.
Chang, J.,Tang, C.Y. and Wu, Y. (2016) Local Independence Feature Screening for Nonparametric and Semiparametric Models by Marginal Empirical Likelihood. Annals of Statistics, 44, 515-539.
Sarkar, S. K.. Fu, Y. and Guo, W. (2016) On Improving Holm’s Procedure Using Pairwise Dependencies. Biometrika , 103, 237-243.
Zhang, W., Leng, C., and Tang, C.Y. (2015) A joint modeling approach for longitudinal studies. Journal of the Royal Statistical Society, Series B.
Guo, W., Li, H., and Sarkar, S. (2014) Further Results on Controlling the False Discovery Proportion. Annals of Statistics , 42(3) 1070-1101.
Cai, T., Li, H., Liu, W., and Xie, J. (2013) Covariate-Adjusted Precision Matrix Estimation with an Application in Genetical Genomics. Biometrika, 100(1), 139-156.
Chang, J., Tang, C.Y., and Wu. Y. (2013) Marginal empirical likelihood and sure independence screening. Annals of Statistics, 41, 2132-2148.
Chen, S. X., Qin, J., and Tang , C.Y. (2013) Mann-Whitney test with adjustments to pre-treatment variables for missing values and observational study. Journal of the Royal Statistical Society, Series B, 81-102.
Fan, J., Liao, Y., and Mincheva, M. (2013) Large Covariance Estimation by Thresholding Principal Orthogonal Complements. Journal of the Royal Statistical Society, Series B, 75(4), 603-680.
Fan, Y., and Tang, C.Y. (2013) Tuning parameter selection for high dimensional penalized likelihood. Journal of the Royal Statistical Society, Series B, 75, 531-552.
Hwang, J. T., and Zhao, Z. (2013) Empirical Bayes Confidence Intervals for Selected Parameters in High Dimensional Data. Journal of the American Statistical Association, 108(502), 607-618.
Krafty, R., and Collinge, W. (2013) Penalized Multivariate Whittle Likelihood for Power Spectrum Estimation. Biometrika, 100(2), 447-458.
Sarkar, S., Chen, J., and Guo, W. (2013) Multiple Testing in a Two-Stage Adaptive Design with Combination Tests Controlling FDR. Journal of the American Statistical Association, 108(504), 1385-1401.
Tang , C.Y., and Fan, Y. (2013) Discussion of Large covariance estimation by thresholding principal orthogonal complements. Journal of the Royal Statistical Society, Series B, 75, 671.