M.A., Ph.D. Harvard University, Statistics
B.A., Harvard College, Mathematics cum laude
Courses I Teach
Introductory Statistics, Biostatistics, Probability, Mathematical Statistics, Regression, Data Analysis, Readings and Research in Statistics, and Statistical Topics
Interests and Areas of Research
Data Analysis, Statistical modeling, Survey sampling, Missing data, Record linkage and administrative data, Bayesian methods, Hierarchical models, Confidentiality, and Teaching Statistics
2018 -present, Member of Education Committee, New England Statistical Society
2017-present, Professor of Mathematics and Statistics, Saint Michael’s College
2011-present, Advisroy Editor, Chance Magazine
2009-2017, Department of Statistics and Biostatistics Center, George Washington University
2009-10, Executive Editor, Chance Magazine
2003-2009, Dept. of Statistics and Center for Survey Statistics & Methodology, Iowa State University
1999-2003, Department of Statistics and National Opinion Research Center, The University of Chicago
1997-1999, Department of Statistics, Harvard University
1996-1997, Department of Statistics, Stanford University
Various summers, Mathematical Statistician, U.S. Census Bureau
1995 – present, Statistical Consultant, http://larsenstatistics.com
Sun, W., Larsen, M.D., and Lachin, J.M. (2014). Methods for a Longitudinal Quantitative Outcome With a Multivariate Gaussian Distribution Multi-dimensionally Censored by Therapeutic Intervention. Statistics in Medicine. 33(8): 1288-1306.
Paik, M., and Larsen, M.D. (2014). Handling nonignorable nonresponse with respondent modeling and the SIR algorithm. Journal Statistical Planning and Inference. 145: 179-189.
Larsen, M.D., Wakim, A.F., Rottach, R., and Cheng, Y. (2013). Nonparametric Comparisons of Current Population Survey Panel Estimates. Chance. 26(4): 35-41.
Larsen, M.D., and Huckett, J. (2012). Multimethod Synthetic Data Generation for Confidentiality and Measurement of Disclosure Risk. International Journal of Information Privacy, Security and Integrity. 1(2/3): 184-204.
Larsen, M.D. (2011). Discussion of “Calibrated Bayes". Statistical Science, 26(2): 175-178.
Barnes, S.A., Larsen, M.D., Schroeder, D.R., Hanson, A., and Decker, P.A. (2010). Missing data assumptions and methods in a smoking cessation study. Addiction, 105, 3, 431-437.
Lavelle, B., Larsen, M.D., and Gundersen, C. (2009). RESEARCH SYNTHESIS: Research strategies for surveys of American Indians. Public Opinion Quarterly. 73: 385-403.
Larsen, M.D. (2008). Discussion of “Modeling and Predicting Probabilities with Outlooks": Prior information as prior observations and a mixture model. Statistica Sinica, 18, n1, 69-75.
Larsen, M.D., and Lu, L. (2007). Comment on “Bayesian Checking of the Second Level of Hierarchical Models" by Bayarri and Castellanos: Cross-validated Posterior Predictive Checks Using Discrepancy Measures. Statistical Science, 22, n3, 359-362.
Larsen, M.D. (2007). Internet Companion for Statistics: Guide and Activities for the Web, second edition, Duxbury Press.
Lahiri, P., and Larsen, M.D. (2005). Regression analysis with linked data. Journal of the American Statistical Association, 100, 222-230.
Larsen, M.D. (2004). Record linkage using finite mixture models. Applied Bayesian Modeling and Causal Inference from Incomplete-Data Perspectives, A. Gelman and X-L. Meng, editors. 309-318.
Larsen, M.D. (2003). Estimation of small-area proportions using covariates and survey data. Journal of Statistical Planning and Inference, 112 (1-2), 89 - 98.
Larsen, M.D., and Rubin, D.B. (2001). Iterative automated record linkage using mixture models. Journal of the American Statistical Association, 96, 32-41.
Chattopadhyay, M., Lahiri, P., Larsen, M.D., and Reimnitz, J. (1999). Composite estimation of drug prevalences for sub-state areas. Survey Methodology, 25, 81-86.
Hsieh, F.Y., Bloch, D.A., and Larsen, M.D. (1998). A simple method for sample size calculation for linear and logistic regression. Statistics in Medicine, 17, 1623-1634.
I was born in Lincoln, Nebraska, and attended Lincoln East High School, where I played cello, studied German, and participated in debate. For college I attended Harvard. I played cello in the Harvard-Radcliffe Orchestra and studied math, Russian, a bit of statistics, and a liberal arts mix of topics. I remained at Harvard for graduate school in statistics during which time I worked summers at the U.S. Census Bureau. My doctoral dissertation topic was on statistical mixture models and their estimation with application to record linkage problems at Census and a Harvard psychology study on infants (clustering based on responses to novel stimuli) . While at The University of Chicago as a senior lecturer, I met my wife Alice. We moved to Iowa and Maryland before coming to Vermont in 2017. We have three children, Lily, Chelsea, and Max, and live in Essex. My wife and I had brief experiences in Vermont before we knew each other, but our first encounter with the state together was through a small statistics workshop on total survey error in Stowe. Subsequently my daughters have attended Farm & Wilderness camps in Plymouth for several summers. I look forward to becoming part of the St. Michael’s community and working to develop Statistics and Data Science here.
Honors and Selected Service
President, Washington Statistical Society, 2016-17
Chair, Survey Research Methods Section, American Statistical Association, 2016
Chief Statistician, Diabetes Prevention Program Outcomes Study (DPPOS), 2015-17
ASA Fellows Committee, 2015-17
NIH Biostatistical Methods and Research Design Study Section, 2013-16
Fellow, American Statistical Association, 2012
Distinguished Scholar, U.S. Census Bureau, 2012
Program Chair, Survey Research Methods Section, American Statistical Association, 2012
President, Sigma Xi chapter at George Washington University, 2011-14
Elected Member, International Statistical Institute, 2010
National Academy of Sciences (NAS) Panel on Census 2010, 2009-14, Standing Committee 2015-2017
Education Officer, Survey Research Methods Section, American Statistical Association, 2009-11
Executive Editor, Chance Magazine, 2008-10
Associate Editor, Annals of Applied Statistics, 2007 - present
Council of Sections Representative, Survey Research Methods Section, American Statistical Association, 2006-8
Faculty Senate Representative, Department of Statistics, Iowa State University, 2007-9
LAS Assembly Representative, Department of Statistics, Iowa State University, 2006-7
Michael Larsen of the Saint Michael's Mathematics and Statistics faculty in recent months: reviewed student papers for the New England Statistical Society’s IBM Student Research Paper competition; refereed articles for statistical journals Biometrika, Annals of Applied Statistics, and Bayesian Analysis; collaborated as a senior statistician for the Veteran’s Administration surveys on Disaster Preparedness of VHA Employees and on Veteran Enrollee’s Health and Health Care Utilization; and, he provided comment on statistical disclosure limitation of low income non-itemized returns in the IRS Survey of Income research file.
(posted June 2019)
Michael Larsen, professor of mathematics and statistics, gave a talk entitled “Statistical methods for an individual patient data meta-analysis” at University of Vermont in November. The talk was given in April of 2018 at the University of Norwich as well. Michael also was coauthor on technical statistical reports to three government agencies: one to the U.S. Veterans’ Administration and two to the IRS Statistics of Income Division. The titles of the reports were “2018 Survey of Veteran Enrollees' Health and Use of Health Care. Survey Methodology Report. Contract No. VA245-17-C-0178. Prepared by Advanced Survey Design, Monterey, CA; September 6, 2018”; second, “Application of multivariate masking and enhanced subsampling to the 2014 individual tax model public use -- le. Report to Internal Revenue Service, Statistics of Income Division; November 15, 2018”: and finally, “Data and Analytic Solutions, Inc. (2018). IRS-SOI variance estimation formula certification suggestions and notes on alternative methods. Statistical Consulting Service TIRNO-17-D-00013 Task Order 0001.” For this report, Michael was bot statistician and primary author. In other career news, Michael joined the Education Committee of the New England Statistical Society, continued to serve as associate editor for the Annals of Applied Statistics and advisory editor for Chance magazine; and served via teleconference on the Panel to Review, National Survey of Early Care and Education (NSECE) 2019: The Provider and Workforce Study, sponsored by the Office of Planning, Research and Evaluation (OPRE), Administration for Children and Families. NORC (December 8, 2017; August 4 and 6, 2018).
(posted January 2019)
Michael Larsen, professor of mathematics and statistics, advises PhD student Yuan Li, who passed his final oral PhD exam at George Washington University. Michael was Li’s PhD advisor in the George Washington Department of Statistics. Michael also was appointed to the Education Committee of the New England Statistical Society, and continues to serve as advisory editor to Chance magazine, associate editor of the Annals of Applied Statistics, and frequent reviewer for ad hoc journals, publishers, and granting agencies.
(posted June 2018)