Welcome to the Homepage

of Dr. Xu-Feng Niu

What I do

My main research areas are time series analysis, spatial statistics, linear and nonlinear models, and statistical applications in environmental studies. As an applied statistician, I believe that a genuine interest in practical problems results in good statistical work.

Environmental data analysis is a field that today is of critical importance in providing the basis of scientific understanding for setting wise public policy on environmental management. Data collected from different spatial locations over a certain period, either by ground-based stations or by satellite, are likely to be correlated spatially and temporally. In recent years, I have worked on the development of space-time models for environmental data, including estimation procedures, model selection and prediction. The models have been applied to stratospheric and tropospheric ozone data for trend assessment. I have also studied extreme value theory for nonstationary environmental time series, applied the results to estimate probabilities of daily maximum ozone concentrations exceeding some specific levels.

I have involved in several interdisciplinary research projects. For example, I collaborate with biologists on studying the role of freshwater input in determining the productivity of river-dominated estuaries, and with meteorologists on studying the predictability of weather phenomena and hurricane activity. Most recently, I have been working with Dan McGee on medical data analysis. Our research involves examining the heterogeneity of results from multiple epidemiological studies.

Return to the Department of Statistics Homepage
Created 7/27/96