Assistant Professor Quantitative Psychology 19 McAlester Hall (573) 884-7866 koehnh@missouri.edu

My research concerns applications of combinatorial optimization methods to scaling/unfolding, clustering/ tree-fitting, and order-constrained matrix decomposition problems, with particular focus on the analysis of individual differences based on sets of multiple proximity matrices, as might be collected from distinct data sources in the context of cross-sectional or longitudinal studies. I have also worked on algorithms for the p-median clustering of large data sets and the clique partitioning problem. A most recent line of research explores the application of complex clustering and optimization routines to item selection and test assembly problems.

Köhn, H.-F. (2006). Combinatorial individual differences scaling within the city-block metric. Computational Statistics & Data Analysis, 51, 931—946.

Köhn, H.-F. (2006). Bookreview: “Branch-and-bound applications in combinatorial data analysis” by Michael J. Brusco and Stephanie Stahl (2005). Psychometrika, 71, 411—413.

Köhn, H.-F. (1997). Strategische Marktforschung bei BBDO [Strategic marketing research at BBDO].
Marktforschung & Management, 41, 33—37.

Köhn, H.-F., Steinley, D., & Brusco, M. (in press). The p-median model as a tool for clustering psychological data. Psychological Methods.

Brusco, M., & Köhn, H.-F. (in press). Clustering qualitative data based on binary equivalence relations: Neighborhood search heuristics for the clique partitioning problem. Psychometrika.

Brusco, M., & Köhn, H.-F. (in press). Exemplar-based clustering via simulated annealing. Psychometrika.

Brusco, M., & Köhn, H.-F. (2008). Technical Comment: “Clustering by passing messages between data points” by Brendan J. Frey and Delbert Dueck, Science, vol. 315: February 16, 2007. Science, February 8, 2008, 726.

Brusco, M., & Köhn, H.-F. (2008). Optimal partitioning of a data set based on the p-median model. Psychometrika, 73, 89—105.

Brusco, M., Köhn, H.-F., & Stahl, S. (2008). Heuristic implementation of dynamic programming for matrix permutation problems in combinatorial data analysis. Psychometrika, 73, 503—522.

Hubert, L., & Köhn, H.-F. (2007). Lower (anti-)Robinson rank represen¬tations for symmetric proximity matrices. In P. Brito, P. Bertrand, G. Cucumel, F. De Carvalho (Eds.), Selected contributions in data analysis and classification, (pp. 495—504). Berlin: Springer.

Hubert, L., Köhn, H.-F., & Steinley, D. (2009). Clusteranalysis. To appear in R. E. Millsap & A. Maydeu Olivares (Eds.), The SAGE handbook of quantitative methods in psychology, (pp. 444—513). Thousand Oaks, CA: Sage.

Hubert, L., Köhn, H.-F., & Steinley, D. (2008). Order-constrained proximity matrix representations: ultrametric generalizations and constructions with MATLAB. To appear in S. Kolenikov, L. A. Thombs & D. Steinley (Eds.), Current methodological developments of statistics in the social sciences, (pp. in press). Hoboken, NJ: Wiley.