Web Reurces

This webpage is under construction.

Research Interests:

• Spatial statistics and spatio-temporal statistics
• Bayesian methodology and hierarchical modeling
• Statistical machine learning, nonparametric methods and kernel methods
• Applications of statistics in environmental sciences and engineering

Currently I am Research Associate with my advisor Dr. Noel Cressie in the Program of Spatial Statistics and Environmental Statistics (SSES).

Projects:

• Dr. Noel Cressie, Dr. Steve Sain and I are working on statistical analysis of Regional Climate model (RCM) outputs. I was on an internship at the National Center for Atmospheric Research (NCAR). A paper is in preparation and I will present our work at the Joint Statistical Meetings 2009 at Washington, DC.

• Dr. Noel Cressie, Dr. Tao Shi and I are working on some interesting problems on spatio-temporal processes. A paper has been submitted and another is in preparation.

• Dr. Noel Cressie, Dr. Desheng Liu and I worked on "Spatial Statistical Analysis of Doctors' Prescription Amounts by Regions". I presented our work in the Joint Statistical Meetings 2007 at Salt Lake City and a paper has been published.

• I was involved in the project "Choosing Smoothing Parameters for Spline Prediction Models with Correlated Errors" while I was on an intership with Commonwealth Scientific and Industrial Research Organization (CSIRO) from June through September in Australia, 2006. My mentors at CSIRO, Richard Morton and Brent Henderson and I collaborated to develop a new method for choosing smoothing parameter with applications to stream salinity measurement data. A paper has been accepted.

Refereed Articles:

• Morton, R., Kang, E. L., and Henderson, B. (2009). Smoothing splines for trend estimation and prediction in time series. Environmetrics, 20, 249-259.

• Kang, E. L., Liu, D., and Cressie, N. (2009). Statistical analysis of small-area data based on independence, spatial, non-hierarchical, and hierarchical models. Computational Statistics and Data Analysis, 53, 3016-3032.

• Cressie, N. and Kang, E. L. (2009). High-resolution digital soil mapping: Kriging for very large datasets, in Proximal Soil Sensing, eds R. Viscarra-Rossel, A. B. McBratney, and B. Minasny. Elsevier, Amsterdam, forthcoming.

• Cressie, N., Shi, T., and Kang, E. L. (2009). Fixed rank filtering for spatio-temporal data, submitted. (Department of Statistics Preprint No. 819, The Ohio State University)

• Kang, E. L., Cressie, N., and Shi, T. (2009). Using temporal variability to improve spatial mapping of satellite data,submitted.

Nonrefereed Articles:

• Cressie, N. and Kang, E. L. (2008). Soil mapping using spatial statistics: Kriging for very large datasets, in Proceedings of First Global Workshop on High Resolution Digital Soil Sensing and Mapping, Vol. I, Sydney, Australia (14pp.).

Manuscripts:

• Kang, E. L., Cressie, N., and Sain, S. R. (2009). Hierarchical spatial random effects model for high-resolution data from regional climate models, in preparation.

• Kang, E. L. and Cressie, N. (2009). Bayesian inference on sptaial random effects model, in preparation.

Presentations:

• Choosing Smoothing Parameters for Spline Prediction Models with Correlated Errors. Presentation for CSIRO Internship at Division of Mathematical and Information Sciences and the Australian National University, Canberra, Australia, August, 2006.

• Spatial Statistical Analysis of Doctors' Prescription Amounts by Regions. The Joint Statistical Meetings, Salt Lake City, August, 2007.

• The 'hockey stick' and the 1990s: a statistical perspective on reconstructing hemispheric temperatures. Statistics in Climate Change Studies Discussion Series, The Program in Spatial Statistics and Environment Statistics (SSES), The Ohio State University, April 4, 2008.

• Statistical Analysis of Small-Area Data Based on Independence, Spatial, Non-hierarchical, and Hierarchical Models. The 22nd Annual Edward F. Hayes Graduate Research Forum, The Ohio State University, April 12, 2008.

• Hierarchical Spatial Random Effects Model for High-resolution Data from Regional Climate Models, The Joint Statistical Meetings, 2009.

Savage's approach to research, via Mosteller: (learned from Professor Xinyi Xu)

• As soon as a problem is stated, start right away to solve it. Use simple examples
• Keep starting from first principles, explaining again and again what you are trying to do
• Believe that this problem can be solved and that you will enjoy working it out
• Don't be hampered by the original problem statement. Try other problems in its neighborhood; maybe there is a better problem than yours
• Work an hour or so on it frequently
• Talk about it; explain it to other people