Statistics

The Department of Mathematical Sciences has a small active group of statisticians. Their interests are in the theory and applications of statistics. Specific research interests include nonparametric correlation and regression, logistic regression and applications, applications of statistics in ecology and natural resource economics, spatial statistics, and discriminant analysis. A general interest statistics seminar meets weekly. Recent topics include bootstrapping, generalized linear models, general statistical techniques using a nonparametric correlation coefficient, S-Plus, and spatial statistical methods. Each year the department offers courses at the junior, senior and graduate levels for majors as well as many services courses for non-majors at all levels. These courses cover mathematical and applied statistics and statistical inference at beginning and advanced levels, computer data analysis, nonparametric statistics, linear models, sampling methods, experimental design, time series and other special topics. Use of computers is an integral component in nearly all statistics courses. Software available includes Data Desk, S-Plus, SPSS, Mathematica and Maple. The department has 2 PC labs, and a departmental network with Unix workstations.  

Faculty

Jonathan Graham

Ph.D., North Carolina State University, 1995
  • Markov Chain Monte Carlo Methods for Modeling the Spatial Pattern of Disease Spread in Bell Pepper, Proceedings of the 1996 Kansas State University Conference on Applied Statistics in Agriculture, pp. 91-108, April 1997.
  • Autologistic Model of Spatial Pattern of Phytophthova Epidemic in Bell Pepper: Effects of Soil Variables on Disease Presence, with M.L. Gumpertz and J.B. Ristaino, Journal of Agriculture, Biology, and Environmental Statistics, Vol. 2, No. 2, pp. 131-156, 1997.

David Patterson

Ph.D., University of Iowa, 1984

  • Constrained Discriminant Analysis via 0/1 Mixed Integer Programming, with R. Gallagher and E. Lee, Annals of Operations Research, 74, 65-88 (1997).
  • Power of Sign Surveys to Monitor Population Trend, with K. Kendall, L. Metzgar and B. Steele, Ecological Applications, 2(4), 422-430 (1992).

Brian Steele

Ph.D., The University of Montana, 1995

  • Ideal Bootstrap Estimation of Expected Prediction Error for k-Nearest Neighbor Classifiers: Applications for Classification and Error Assessment, with D. Patterson, accepted by Statistics and Computing.
  • Estimation and Mapping of Misclassification Probabilities for Thematic Land Cover Maps, with J.C. Winne and R.L. Redmond, Remote Sensing and Environment, 66, 192-202, (1998).
  • A Modified EM Algorithm for Estimation in Generalized Mixed Models, Biometrics, 52, 1295-1310, (1996).

Faculty Emeriti

Rudy Gideon

Ph.D., University of Wisconsin, 1970.

  • Currently preparing 1/2 day workshop for the August ASA meeting on the general use of correlation coefficients in statistical estimation.
  • A Rank Correlation Coefficient Resistant to Outliers, JASA, Vol. 82 (1987), no. 398, pp. 656-666.
  • The Nonparametric Correlation Coefficient as a Comprehensive Robust Statistical Tool, a talk in an invited speaker session, Western Regional Meeting of IMS, Biometric Society, June 1994.

Don Loftsgaarden

Ph.D., Montana State University, 1964

  • Statistical Abstract of Undergraduate Programs in the Mathematical Sciences in the United States, Fall 1995 CBMS Survey, with Donald C. Rung and Anne E. Watkins, MAA Reports No. 2, The Mathematical Association of America, 1997, 189 pages. Funded by the National Science Foundation.
  • Statistical Abstract of Undergraduate Programs in the Mathematical Sciences and Computer Science in the United States, 1990-1991 CBMS Survey, with Donald Albers, Donald Rung and Anne Watkins, MAA Notes No. 23, The Mathematical Association of America, 1992, 173 pages. Funded by the National Science Foundation.
  • Constructing and Testing Logistic Regression Models for Binary Data: Applications to the National Fire Danger Rating System, with Patricia Andrews, May 1992, 36 pages. U.S. Forest Service, Intermountain Research Station, General Technical Report INT-286.