Department of Mathematics and Statistics

Statistics

Faculty

Xiaoli Gao
Associate Professor
x_gao2@uncg.edu
https://sites.google.com/a/uncg.edu/xiaoli-gao/
Research Interests: High Dimensional Data Analysis, Statistical Genetics

Dr. Gao received her B.S. in Probability and Statistics from Anhui University, China in 2000 and her M.S. and Ph.D. in Statistics from the University of Iowa in 2005 and 2008, respectively. Her primary research areas of interest include high-dimensional data analysis, change point, copy number analysis, and survival analysis. With the development of technology, more and more big data sets arise from health sciences, social sciences, and biological sciences. One important question is to find those important features from tens of thousands potential ones. Dr. Gao has special expertise in handling those large-p-small-n problems. She is also looking forward to having a big-data science research group in Triad area. Before joining UNCG, Dr. Gao held an Assistant Professor position at Oakland University in Michigan. She was also served as an intern biometrician at Merck & Co., Inc. in summer 2007 and a research assistant in Statistical consulting center at the University of Iowa in Summer 2005. Some of her recent publications are:

Gao, X.L. and Huang, J. (2010) A Robust Penalized Method for the Analysis of Noisy DNA Copy Number Data. BMC Genomics, 11:517.

Gao, X.L. and Huang, J. (2010). Asymptotic analysis of high-dimensional LAD regression with Lasso. Statistica Sinica, 20, 1485-1506

Gao, X.L. and Fang, Y.X. (2011). A note on the generalized degrees of freedom under the L1 loss function, Journal of Statistical Planning and Inference, 141, 677-686

Gillies, C. E., Gao, X.L., Patel, N.V., Siadat, M.R., Wilson, G.D.(2012). Improved Feature Selection by Incorporating Gene Similarity into the LASSO, International Journal of Knowledge Discovery in Bioinformatics, 3(1), 1-13, DOI: 10.4018/jkdb.2012010101

Zeng, X., Xiao, C., Rehman, A. and Gao, X.L. (2013). Characterization of Dynamic Interaction between Electro-generated Superoxide Radical and Cation in Ionic Liquids by EQCM, under revision by Journal of the Electrochemical Society


Sat Gupta
Professor
sngupta@uncg.edu
http://www.uncg.edu/mat/faculty/sngupta/
Research Interests:Sample Surveys, Biostatistics, Time Series Forecasting

Dr. Gupta received PhD in mathematics from University of Delhi (1977) and PhD in statistics from Colorado State University (1987). He taught at University of Delhi for 6 years, at University of Southern Maine for 18 years, and has been at UNC Greensboro since 2004. He became a Full professor in 1997. His main research area is sampling designs, particularly designs needed for collecting information on sensitive topics where there is a greater likelihood of respondent evasiveness and untruthfulness. He has collaborated with researchers from many fields including biology, marine biology, education, anthropology, psychology, medicine, nursing, and computer science. Some of these collaborative works have been funded by NSF, NIH and other funding agencies. Some of his recent publications are:

Gupta, S., Shabbir, J. and Sehra, S. (2010). Mean and Sensitivity Estimation in Optional Randomized Response Models. Journal of Statistical Planning and Inference, Vol. 140, 2870-2874

Jones, E., Gupta, S. Murphy, A. and Norris, F. (2011): Inequality, Social Support and Post-Disaster Mental Health in Urban Mexico, Human Organization (Journal of the Society for Anthropologists), Vol. 70, No. 1, 33-43

Gupta, S., Shabbir, J., Sousa, R., Corte-Real, P. (2012): Regression Estimation of the Mean of a Sensitive Variable in the Presence of Auxiliary Information. Communications in Statistics – Theory and Methods, Vol. 41, 2394-2404

Letvak, S, Ruhm, C. J. and Gupta, S. (2012). Nurses’ Presenteeism and its effects on Self- Reported Quality of Care and Costs, American Journal of Nursing, Vol. 112, No. 2, 30-38

Shug, G., Gupta, S., Cowgill, L., Sciulli, P., and Blatt, S. (2013). Panel Regression Formulas for Stature and Body Mass Estimation in Immature Human Skeletons, to appear in the Journal of Archaeological Science


Scott Richter
Associate Professor
http://www.uncg.edu/~sjricht2/
Research Interests: Non-Parametric Methods, Multivariate Analysis

Dr. Richter received a PhD in Statistics from Oklahoma State University (1997). His current research interests are in the area of nonparametric methods, especially those based on resampling. Recent work has focused on permutation multiple comparison procedures. As Director of the Statistical Consulting Center, Dr. Richter has consulted extensively with faculty and graduate student researchers from biological, health and social sciences. These interactions have often led to collaborations resulting co-authored publications and externally funded projects. Recent publications:

Taylor, J., Waxman, J., Richter, S. & Shultz, S. (In press). Evaluation of the effectiveness of anterior cruciate ligament injury prevention program training components: a systematic review and meta-analysis. British Journal of Sports Medicine. (DOI: 10.1136/bjsports-2013-092358)

Richter, S. J. and McCann, M. H. (2013). Simultaneous Multiple Comparisons with a Control Using Medians and Permutation Tests. Statistics and Probability Letters, 83(4) 1167-1173. (DOI:10.1016/j.spl.2013.01.014)

Lacey, E. P., Lovin, M. E., Richter, S. J. (2012). Fitness Effects of Thermoregulation in a Thermally Changing Environment. The American Naturalist, 180(3), 342-353. (DOI: 10.1086/666987)

Richter, S. J. and McCann, M. H. (2012). Using the Tukey-Kramer Test as the Omnibus Test in the Hayter-Fisher Procedure. British Journal of Mathematical and Statistical Psychology, 65, 499-510. (DOI:10.1111/j.2044-8317.2012.02041.x)

Junio, H. A., Sy-Cordero, A. A., Ettefagh, K. A., Burns, J. T., Micko, K. T., Graf, T. N., Richter, S. J., Cannon, R. E. Nicholas H. Oberlies, and Nadja B. Cech (2011). Synergy Directed Fractionation of Botanical Medicines: A Case Study with Goldenseal (Hydrastis canadensis). Journal of Natural Products, 74, 1621-1629. (DOI: 10.1021/np200336g)


Haimeng Zhang
Associate Professor
h_zhang5@uncg.edu
http://math.msstate.edu/people/bio.php?rec=368
Research Interests: Survival Analysis, Spatial Statistics, Applied Probability

Dr. Zhang received his Master's degree in computer engineering in 1996 and his Ph.D. degree in applied mathematics with concentration in statistics in 1998, both from the University of Southern California at Los Angeles, CA. He was an assistant professor and then an associate professor in Concordia College at Moorhead, MN from 1998 to 2008. He became an associate professor of statistics at Mississippi State University from 2008 to 2013. His research interests are in the fields of spatial statistics, survival analysis, and applied probability. He has been collaborating with researchers from many fields such as geography, biology, computer science, and health science. His current NSF-supported research focuses on the statistical analysis of global-scale processes and phenomena using spatio-temporal data collected from global networks and satellite sensors. Some of his recent publications are:

Huang, C., Zhang, H., and Robeson, S. (2012). A simplified representation of the covariance structure of axially symmetry processes on the sphere, Statistics and Probability Letters, 82, 1346 - 1351

Huang, C., Zhang, H., and Robeson, S. (2011). On the validity of commonly used covariance and variogram functions on the sphere, Mathematical Geosciences, 43, 721-733

Brooks, C. and Zhang, H. (2010). A null model of community disassembly effects on vector-borne disease risk. Journal of Theoretical Biology, 264, 866 - 873.

Goldstein, L. and Zhang, H. (2009). Efficiency calculations for the maximum partial likelihood estimator in nested-case control sampling, Bernoulli, 15, 569 - 597.


Insuk Shim
Lecturer
i_shim@uncg.edu
http://www.uncg.edu/mat/people/people.php?username=i_shim

My research interest is on Generalization of Multivariate Markovian Arrival Process.The applications were made with level-independent MAP which has only possible one-step transition rate in most cases. If we can generalize MAP that includes level-dependent transitions of MAP which will have finitely many transition rates from one state to other states, it will be more useful to analyze the real situation. Multivariate MAP process can be introduced as a generalization of the MAP. Multivariate MAP can be generally used to count multiple types of events. For example, the resulting probability distributions from the Multivariate MAP show normal, abnormal behaviors, long-tail breakthrough curves depending on the MAP structures. The research will find a rich structure of the Multivariate MAP and flexibility so the result can apply for modeling groundwater solute transport, queueing networks, and other real world problems.

Ph.D. Students

Vivian Chen - Advisor Haimeng Zhang
Jeong Sep Sihm - Advisor Sat Gupta
Chris Vanlangenberg - Advisor (undecided)
Tanja Zatezalo- Advisor Sat Gupta