• Assistant Professor
• Ph.D., Statistics, U. Minnesota, 2003
• M.S., Statistics, U. Minnesota
• B.S., Computer Science, Carnegie Mellon
• Personal web site

Summary of research interests

Dr. Haran's research interests are primarily in three areas: statistical computing, spatial modeling for problems in environmental science, and statistical techniques in software engineering. His statistical computing work focuses on finding ways to construct efficient and automated Markov chain Monte Carlo (MCMC) algorithms for estimating properties of complicated distributions. He has worked on algorithms that produce accurate estimates quickly and with minimal user intervention, while at the same time providing some theoretical guarantees regarding the accuracy of resulting estimates. His spatial modeling work is motivated by research problems in diverse areas including Geosciences, Ecology and Epidemiology. He has ongoing collaborations with faculty members from each of these disciplines, and some recent projects have included climate change research, studying invasive plant species and space-time models for crop epidemics. This work is, in turn, leading to methodological work in analyzing large spatial data sets and related research on using Gaussian processes for emulating computer models, studying and applying spatial generalized linear models, and research in computing for spatial models. Dr.Haran's collaborations with software engineers have involved using statistical classification techniques to model failures in large software systems.

Representative publications

Haran, M., Bhat, K.S., Molineros, J, and De Wolf, E. (2008) Estimating the risk of a crop epidemic from coincident spatiotemporal processes, Journal of Agricultural, Biological and Environmental Statistics (to appear).

Flegal, J.M., Haran, M., and Jones, G.L. (2008) Markov chain Monte Carlo: Can we trust the third significant figure? Statistical Science,23,250--260.

Haran, M. and Tierney, L. (2008), Exact and approximate sampling for Markov random field models (under review).

Jones, G.L., Haran, M., Caffo, B.S. and Neath, R. (2006), Fixed Width Output Analysis for Markov chain Monte Carlo, Journal of the American Statistical Association, 101:1537--1547.

Haran, M., Karr,A.F., Last,M., Orso,A. Porter,A., Sanil, A.P. and Fouche, S. (2007) Techniques for Classifying Executions of Deployed Software to Support Software Engineering Tasks, IEEE Transactions on Software Engineering, 33,5:287-304.

Last updated: 1 Sept 2008