 | |  | | James M. (Jim) Landwehr
Director, Data Analysis Research
"The most important maxim for data analysis to heed… is this: Far better an approximate answer to the right question, which is often vague, than an exact answer to the wrong question, which can always be made precise. - John W. Tukey, 1962" |
| My Research | | My research has both applied problem area content, and statistical methodology content. Over time and from problem to problem, the focus shifts. I’ve found that it is generally interesting, challenging and rewarding to attempt to solve the real problem given the constraints that exist, but doing so often raises interesting methodological issues. Ideally, these correspond to two sides of the same coin and can be attacked together—but usually the world is not ideal. Areas of statistical methodology where I have done research and published include cluster analysis, categorical data analysis, logistic regression, modeling and graphics. |
| Projects | | Current project areas include the analysis and visualization of data from network testing and operations, and also of data from complicated workflow processes. While the substance of these topics are quite different, they both involve massive data streams or data bases that need to be handled relatively automatically, The challenge is to devise procedures to do this and understand when they do and do not work. Previously, I’ve worked on modeling and process improvement for manufacturing optical fiber, on experimentation to improve soldering small components, and on extracting information from large sets of customer records. Each topic has been fascinating and challenging. |
| Publications | I have more than 60 research publications in statistics and applications journals. A co-authored article in Technometrics, "Interplay between physics and statistics for modeling optical fiber bandwidth," won the American Statistical Association’s Outstanding Statistical Application Award in 2003. I served as Editor of The American Statistician from 1997-1999. I also have a longstanding interest in K-12 statistics education and, with support from NSF grants to several large projects, have co-authored five books that introduce modern ideas of data analysis and statistics into grade 7-12 classrooms by supplementing standard math textbooks. |
|
|
| |
