Congratulations August 2009 Graduates!

08-14-2009

The Department of Statistics would like to congratulate all of its August 2009 graduates. On August 8, 2009, Purdue University and the Department of Statistics awarded degrees to the following people:

Ph.D. Graduates - (Advisor) Dissertation Title

• Mr. Yunxiao He - (Chuanhai Liu) "Improving the EM Algorithm for Maximum Likelihood Inference"
• Ms. Lanqing Hua - (Bruce A. Craig) "Statistical Inference of Protein Structure Using Small-Angle X-Ray Scattering Data"
• Mr. Paul Kidwell - (William S. Cleveland, Guy Lebanon) "Methods for Analyzing Rankings and Network Intrusion Detection"
• Mr. Ryan Martin - (Jayanta K. Ghosh, Chuanhai Liu) "Fast Nonparametric Estimation of a Mixing Distribution with Application to High-Dimensional Inference"
• Ms. Cherie Ochsenfeld - (Rebecca W. Doerge, Kristofer Jennings) "Mixed Models in Quantitative Trait Loci and Association Mapping with Bootstrap Threshold"
• Mr. Yang Zhao - (Guy Lebanon) "Local Likelihood Modeling of the Concept Drift Phenomenon"

M.S. Graduates

• Mr. Douglas Baumann
• Ms. Hongmei Ding
• Ms. Fang Liu
• Ms. Jiao Song
• Mr. Yifeng Yang
• Mr. Wei Zhang

Graduate Certificates

• Mr. Melvin Lamboy-Ruiz

Undergraduates in Statistics

• Mr. Jacob T. Dummitt
• Mr. Scott M. Moeller

Actuarial Science Majors

• Ms. Melanee N. Dallas
• Mr. Jacob T. Dummitt

So far for the year 2009, the Department of Statistics has graduated 10 Ph.D. students, 19 M.S. students, 5 Graduate Certificate students, 31 Undergraduate Statistics students and 24 Actuarial Science students.

We would like to highlight the achievements of one of the Department's August 2009 graduates, Dr. Paul Kidwell, whose advisors were Professor William S. Cleveland and Professor Guy Lebanon. Kidwell's research is highly interdisciplinary, combining ideas from probability, statistics, combinatorics, and computation. He developed a framework for modeling ranked data that is statistically consistent without parametric assumptions, and is computationally efficient. In addition to applying it to real world data, Kidwell also studied its statistical properties and characterized its bias and variance. This was done by using generating functions to enumerate inversions which constitute Kendall's tau - a popular distance for permutations.

These contributions are important for analyzing preference data such as election results, movie recommendations, and psychological surveys. In addition to visualizing the data and estimating the underlying distribution they lead to a new theory of survey design where surveys involving preferences may be designed to trade off statistical accuracy for survey complexity.

Kidwell has accepted a post-doc position at the Lawrence Livermore National Lab.

Best wishes to all of our graduates. We look forward to hearing from you!