Chaoxiong (Michelle) Xia, Ph.D.

Associate Professor

Michelle Xia earned her Ph.D. in statistics from the University of British Columbia, her master's degree in actuarial science from the University of Calgary and dual bachelor's degrees — one in insurance and one in mathematical statistics and probability — from Nankai University.

In addition to her research, teaching and consulting at NIU, Xia has more than seven years of professional experience as an actuary, predictive modeler and statistician in the insurance and healthcare sectors.

Education

Ph.D., University of British Columbia — Machine Learning, Predictive Analytics, Actuarial Science, Computational Algorithms

Research

Xia develops statistical methodology at the intersection of Bayesian inference, machine learning and actuarial science, with a central focus on misclassification, misrepresentation and missing data — problems of fundamental importance in insurance ratemaking, epidemiology and health research. Her work has produced Bayesian mixture regression frameworks, EM algorithms and frequentist inference methods that explicitly account for data quality issues, with applications to fraud detection, pension mortality and healthcare analytics. She has been supported by the Casualty Actuarial Society and the Society of Actuaries and has published in ASTIN Bulletin, the Canadian Journal of Statistics, Statistics in Medicine and the North American Actuarial Journal.

Selected Publications

Gustafson, P., Gilbert, M., Xia, M., Michelow, W., Robert, W., Trussler, T., McGuire, M., Paquette, D., Moore, D., and Gustafson, R. (2013). Impact of statistical adjustment for frequency of venue attendance in a venue-based survey of men who have sex with men. American Journal of Epidemiology, 177, 1157-1164.

Xia, M., and Gustafson, P. (2012). A Bayesian method for estimating prevalence in the presence of a hidden sub-population. Statistics in Medicine, 31, 2386-2398.