Mathematics and Statistics Colloquium

Meet-n-Greet: 3:30 p.m., Talk: 4:00 p.m.

Speaker: Dr. Sixia Chen, University of Oklahoma
Title: General-purpose multiply robust data integration procedure for combining probability and non-probability samples
Host: Dr. Zheng Xu

ABSTRACT:

Recently, there has been an increased interest in combining probability and nonprobability samples. Non-probability sample are cheaper and quicker to conduct. However, the resulting estimators are vulnerable to bias as the selection probabilities are unknown. To adjust for the potential bias, estimation procedures based on parametric or nonparametric models has been discussed in the literature. The validity of the resulting estimators depends on the validity of the underlying models. Also, nonparametric approaches suffer from the curse of dimensionality and poor efficiency. We propose a data integration approach by combining multiple outcome regression models and propensity score models. The proposed approach can be used for estimating general parameters including totals, means, distribution functions and percentiles. The resulting estimators are multiply robust in the sense that they remain consistent if all but one model are mis specified. The asymptotic properties of point and variance estimators will be established. The results from a simulation study shows the benefits of the proposed method in terms of bias and efficiency.

SPEAKER BIO:

Dr. Sixia Chen is an assistant professor at department of biostatistics and epidemiology of University of Oklahoma Health Sciences Center. Dr. Chen got BA degree in Math from Fudan University at China and PhD degree in Statistics at Iowa State University. His research interests include survey sampling, missing data analysis, statistical disclosure control, empirical likelihood method, and big data. Dr. Chen had more than 46 publications in peer reviewed journals including Biometrika, Annals of Applied Statistics, and Statistica Sinica. He is now serving as the Associate Editor for Journal of Korean Statistical Society, Journal of Survey Statistics and Methodology, and Scandinavian Journal of Statistics. Dr. Chen is serving as the director of novel methodology unit of Oklahoma Shared Clinical and Translational Research at OUHSC. Dr. Chen performed as PI for several local and NIH funded projects.