Principal Investigator, The Methodology Center
H.E. Robbins Professor, Statistics
Research Professor, The Institute for Social Research
Professor, Psychiatry
Department of Statistics
439 West Hall, 1085 S. Univ.
University of Michigan
Ann Arbor, MI 48109-1107
734-647-3684
Education
Ph.D., University of North Carolina, 1989 (Statistics)
B.S., Louisiana State University, 1980 (Mathematics)
Research Interests
My current primary interest is in causal inference and multi-stage decisions sometimes called adaptive interventions or adaptive treatment strategies. These are individually tailored treatments; formally, an adaptive treatment strategy is a sequence of decision rules that specify when to alter the therapy and specify which intensity or type of subsequent therapy should be offered. The decision rules employ variables such as patient response, risk, burden, adherence, and preference, collected during prior therapy. In an adaptive treatment strategy, the decision rules are specified prior to the beginning of the initial therapy. These regimes hold the promise of maximizing treatment efficacy by avoiding ill effects due to over-treatment and by providing increased treatment levels to those who can benefit. Once developed, the decision rules can be used to augment/enhance clinical judgment. I am particularly interested in developing statistical methods and experimental designs that can be used in formulating adaptive treatment strategies. This work is funded by National Institute on Drug Abuse and by National Institute of Mental Health.
Current Projects and Collaborators
I am working on multiple related projects all aimed at how best to collect and use data in the development of adaptive treatment strategies. My collaborators on these projects are Daniel Almirall, Linda Collins, and Inbal Nahum-Shani.
Selected Honors and Awards
2011: Elected a Member of the International Statistical Institute.
2007-2008: Invited Fellow at the Center for Advanced Study in the Behavioral Sciences, Stanford University
2007-2009: Editor of The Annals of Statistics (with B. Silverman)
2005: Presented the Clifford C. Clogg Memorial Lecture, Sociology and Statistics Departments, Pennsylvania State University
2004: Awarded a University of Michigan Collegiate Professorship
2002: Elected a Fellow of the American Statistical Association
2000: Elected a Fellow of the Institute of Mathematical Statistics
1999: NSF Mid-Career Methodological Opportunities Fellowship
Selected Recent Publications
Peer-Reviewed Articles
Almirall, D., Compton, S. N., Rynn, M. A., Walkup, J. T., & Murphy, S. A. (2012). SMARTer discontinuation trial designs for developing an adaptive treatment strategy. Journal of Child and Adolescent Psychopharmacology, 22(5), 364-374. PMCID: PMC3482379
Fonteneau, R., Murphy S. A., Wehenkel, L., & Ernst, D. (2012). Batch mode reinforcement learning based on the synthesis of artificial trajectories. Annals of Operations Research. Advance online publication. doi: 10.1007/s10479-012-1248-5 PMC Journal- In process
Lizotte, D. J., Bowling, M., & Murphy, S. A. (2012). Linear fitted Q-iteration with multiple reward functions. Journal of Machine Learning Research, 13, 3253-3295. PMC Journal- In process
Little, R. J., D’Agostino, R., Cohen, M. L., Dickersin, K., Emerson, S. S., Farrar, J. T., Frangakis, C., Hogan, J. W., Molenberghs, G., Murphy, S. A., … Stern, H. (2012). The prevention and treatment of missing data in clinical trials. New England Journal of Medicine 367, 1355-1360. PMC Journal- In process
Almirall, D., Lizotte, D., & Murphy, S. A. (2012). Comment: SMART design issues and the consideration of opposing outcomes: Discussion of “Evaluation of Viable Dynamic Treatment Regimes in a Sequentially Randomized Trial of Advanced Prostate Cancer” by Wang, Rotnitzky, Lin, Millikan, and Thall. Journal of the American Statistical Association, 107, 509-512. PMC Journal- In process
Nahum-Shani, I., Qian, M., Almirall, D., Pelham, W., Gnagy, B., Fabiano, G., … Murphy, S. A. (2012). Experimental design and primary data analysis methods for comparing adaptive interventions. Psychological Methods, 17, 457-77. PMC Journal- In process
Nahum-Shani, I., Qian, M., Almirall, D., Pelham, W., Gnagy, B., Fabiano, G., … Murphy, S. A. (2012). Q-learning: A data analysis method for constructing adaptive interventions. Psychological Methods, 17, 478-494. PMC Journal- In process
Almirall, D., Compton, S. N., Gunlicks-Stoessel, M., Duan, N., & Murphy, S. A. (2012). Designing a pilot sequential multiple assignment randomized trial for developing an adaptive treatment strategy. Statistics in Medicine, 31(17), 1887-1902. PMCID: PMC3399974
Lei, H., Nahum-Shani, I., Lynch, K., Oslin, D., & Murphy, S. A. (2012). A "SMART" design for building individualized treatment sequences. The Annual Review of Clinical Psychology, 8, 21-48. PMC Journal- In progress
Gunter, L., Zhu, J., & Murphy, S. A. (2011). Variable selection for qualitative interactions in personalized medicine while controlling the family-wise error rate. Journal of Biopharmaceutical Statistics, 21, 1063-1078. PMCID: PMC3003934
Shortreed, S. M., Laber, E., Lizotte, D. L., Stroup S., Pineau, J., & Murphy, S. A. (2011). Informing sequential clinical decision-making through reinforcement learning: An empirical study. Machine Learning, 84(1), 109-136. PMCID: PMC3143507
Gunter, L., Zhu, J., & Murphy, S. A. (2011). Variable selection for qualitative interactions. Statistical Methodology, 1(8), 42-55. PMCID: PMC3003934
Qian, M., & Murphy, S. A. (2011). Performance guarantees for individualized treatment rules. Annals of Statistics, 39(2), 1180-1210. PMCID: PMC3110016
Li, Z., & Murphy, S. A. (2011). Sample size formulae for two-stage randomized trials with survival outcomes. Biometrika 98(3): 503-518. PMCID:PMC3254237
Almirall, D., McCaffrey, D. F., Ramchand, R., & Murphy, S. A. (2011). Subgroups analysis when treatment and moderators are time-varying. Prevention Science. Advance online publication. doi: 10.1007/s11121-011-0208-7 PMCID: PMC3135740
Deng, K., Pineau, J., & Murphy, S. A. (2011). Active learning for personalizing treatment. Proceedings of the ADPRL - 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (pp. 32-39). Piscataway, NJ: IEEE. doi: 10.1109/ADPRL.2011.5967348
Deng, K., Pineau, J., & Murphy, S. A. (2011). Active learning for developing personalized treatment. Proceedings of the Twenty-seventh Conference on Uncertainty in Artificial Intelligence 2011 (pp. 161-168). Corvallis, OR: AUAI Press.
Almirall, D., Ten Have, T., & Murphy, S. A. (2010). Structural nested mean models for assessing time-varying effect moderation. Biometrics, 66(1), 131-139. PMCID: PMC2875310
Fonteneau, R., Murphy, S. A., Wehenkel, L., & Ernst, D. (2010). A cautious approach to generalization in reinforcement learning. In J. Filipe, A. Fred, & B. Sharp (Eds.), Proceedings of the 2nd International Conference on Agents and Artificial Intelligence, Vol.1 (pp.64-73).
Fonteneau, R., Murphy, S. A., Wehenkel, L., & Ernst, D. (2010). Model-free Monte Carlo-like policy evaluation. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 9, 217-224.
Lizotte, D., Bowling, M., & Murphy, S. A. (2010). Efficient reinforcement learning with multiple reward functions for randomized controlled trial analysis. Proceedings of the 27th International Conference on Machine Learning (pp.695-702).
McGowan, H. M., Nix, R. L., Murphy, S. A., Bierman, K. L., & Conduct Problems Prevention Research Group. (2010). Investigating the impact of selection bias in dose-response analyses of preventive interventions. Prevention Science, 11(3), 239-251. PMCID: PMC3044506
Oetting, A. I., Levy, J. A., Weiss, R. D., & Murphy, S. A. (2010). Statistical methodology for a SMART design in the development of adaptive treatment strategies. In P.E. Shrout, (Ed.), Causality and psychopathology: Finding the determinants of disorders and their cures. Arlington, VA: American Psychiatric Publishing.
Book Chapters
Oetting, A. I., Levy, J. A., Weiss, R. D., & Murphy, S. A. (2011). Statistical methodology for a SMART design in the development of adaptive treatment strategies. In P. E. Shrout, K. M. Keyes, & K. Ornstein (Eds.), Causality and psychopathology: Finding the determinants of disorders and their cures (pp. 179-205). Arlington VA: American Psychiatric Publishing.
Almirall D., Coffman C. J., Yancy W. S., & Murphy S. A. (2010). Maximum likelihood estimation of the structural nested mean model using SAS PROC NLP. Analysis of Observational Health-Care Data Using SAS. D. Faries, A. Leon, J.M. Haro, B. Obenchain (Editors).
Presentations
Almirall, D., Collins, L. M., & Murphy, S. A. (2012, November). Getting SMART about the design of experimental trials for the development of adaptive health interventions. Presented at the second Innovative Methods Program for Advancing Clinical Trials, Raleigh, NC.
Almirall, D., & Murphy, S. A. (2012, October). Piloting and sizing sequential multiple assignment randomized trials na dynamic treatment regime development. Presented at the International Conference on Statistics and Combinatorics, Greensboro, NC.
Almirall, D., McCaffrey, D., Griffin, B. A., Ramchand, R., & Murphy, S. A. (2012, September). Examining moderated eects of additional adolescent substance use treatment: Structural nested mean model estimation using inverse-weighted regression-with-residuals. Presented at George Mason University, Fairfax, VA.
Murphy, S. A. (2012, September). Treatment effect heterogeneity and dynamic treatment regime development. Presented at the University of Alberta, Edmonton, AB, Canada.
Laber, E. B., Lizotte, D. J., Qian, M., Pelham, W. E., & Murphy, S. A. (2012, August). Statistical inference in dynamic treatment regimes. In F. Wei (Chair), New methods for analyzing clinical trials. Symposium conducted at the Joint Statistical Meetings, San Diego, CA.
Murphy, S. A. (2012, August). Taking advantage of treatment effect heterogeneity in dynamic treatment regime development. In K. Imai (Chair), Treatment effect heterogeneity in causal inference. Invited paper presented at the Joint Statistical Meetings, San Diego, CA.
Murphy, S. A. (2012, August). Dynamic treatment regime development. In J. Cheng (Chair), Roundtable discussion: Statistics in epidemiology. Presented at the Joint Statistical Meetings, San Diego, CA.
Murphy, S. A. (2012, August). Sequential, multiple assignment, randomized trials and treatment policies. In S. Saria (Chair), Active collaborative problem brainstorming. Presented at the Meaningful Use of Complex Medical Data meeting, Los Angeles, CA.
Almirall D., McCaffrey D. F., Griffin B. A., Ramchand, R., & Murphy S. A. (2012, July). Examining moderated effects of additional adolescent substance use treatment: Structural nested mean model estimation using inverse-weighted regression-with-residuals. Invited Seminar presented at the Asia Pacific Rim Meeting of the International Mathematical Statistics Society, Tsukubu, Japan.
Deng, K., Pineau, J., & Murphy, S. A. (2012, July). Active learning for developing personalized treatment. In Y. Liu (Chair), Recent advances in statistical machine learning. Invited paper presented at the Joint Statistical Meetings, San Diego, CA.
Laber, E., & Murphy, S. A. (2012, July). Adaptive confidence intervals for regression coefficients in Q-learning. Workshop presented at Statistical Inference in Complex/High-Dimensional Problems, University of Vienna, Austria.
Murphy, S. A. (2012, June). Adaptive confidence intervals for nonregular parameters. Invited plenary talk at the Conference on Statistical Learning and Data Mining, University of Michigan, Ann Arbor, MI.
Almirall D., & Murphy S. A. (2012, June). Getting SMART about developing individualized, adaptive health interventions. Workshop presented for Methods Work, Chicago, IL.
Murphy, S. A. (2012, May). Piloting and sizing sequential, multiple assignment, randomized trials in dynamic treatment regime development. Workshop presented at 2012 Atlantic Causal Inference Conference, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD.
Li, Z., & Murphy, S. A. (2012, April). Sizing sequential, multiple assignment, randomized trials for survival analysis. Presented at the 2012 Spring Meeting of the Eastern North American Region of the International Biometric Society, Washington DC.
Murphy, S. A. (2012, April). Confidence intervals, Q-learning, and dynamic treatment regimes. Invited talk presented at Time for Causality Workshop, University of Bristol, Bristol, United Kingdom.
Murphy, S. A. (2012, April). Getting SMART about adapting interventions. Invited talk presented at Early Childhood Interventions Working Group Inaugural Conference, University of Chicago, Chicago, IL.
Murphy, S. A. (2012, March). SMART clinical trial designs for developing dynamic treatment regimes. Invited talk presented the 10th Annual ASA CT Chapter Mini-Conference: Emerging Statistical Issues in Clinical Trials, Yale University West Campus, Orange, CT.
Murphy, S. A. (2012, March). SMARTs: New data and challenges. Presented at the Oberwolfach meeting on Frontiers in Nonparametric Statistics, Oberwolfach, Germany
Almirall D., Compton S. N., & Murphy S. A. (2012, March). Developing adaptive health interventions: Getting SMART. Invited talk presented at the AIMS Center, University of Washington, Seattle, WA.
Laber, E. & Murphy, S. A. (2012, February). Adaptive confidence intervals for non-regular parameters. Department of Statistical Science, Cornell University.
Murphy, S. A. (2011, December). Adaptive confidence intervals for non-regular parameters. Presented at the Department of Biostatistics, Graduate School of Public Health, University of Pittsburgh.
Murphy, S. A. (2011, December). Getting SMART about adapting interventions. Presented at the HIV Intervention Science Program for Underrepresented New Investigators, Columbia University.
Almirall, D., & Murphy, S. A. (2011, November). Developing dynamic, sequential interventions that optimize mental health outcomes: Novel clinical trial design and data analysis strategies. Seminar presented at the Association of Behavioral and Cognitive Therapies Convention, Toronto, Canada.
Laber, E. & Murphy, S. A. (2011, September). Adaptive confidence intervals for non-regular parameter. Institute for Mathematical Research, High- Dimensional Problems in Statistics Conference, Zurich, Switzerland.
Murphy, S. A., & Almirall, D. (2011, June). Getting SMART about developing individualized, adaptive health interventions. Workshop presented at the University of Minnesota NIMH Prevention Center, Twin Cities, MN.
Murphy, S. A., Almirall, D., Oslin, D., & Jones, H. (2011, June). Getting SMART about developing individualized sequences of health interventions. Workshop presented at the College on Problems of Drug Dependence (CPDD), Hollywood, FL.
Murphy, S. A., McKay, J., Pelham, W., Jones, H., & Kasari, C. (2011, June). Developing dynamic, sequential treatments that optimize mental health outcomes: Experiences with a novel clinical trial design. Workshop presented at the New Clinical Drug Evaluation Unit (NCDEU), Boca Raton, FL.
Almirall, D., Collins, L. M., & Murphy, S. A. (2011, June). Experimental designs for developing adaptive treatment strategies. Presented at the Childhood Obesity Prevention and Treatment Research (COPTR) research program. Teleconference.
Murphy, S. A. (2011, May). Practical application of adaptive treatment strategies in trial design and analysis. Paper presented at the Society for Clinical Trials Annual Meeting, Vancouver, BC, Canada.
Murphy, S. A. (2011, May). Time varying treatments and optimal treatment strategies. Workshop presented at the Causal Inference in Health Workshop, Le Centre de recherché mathematiques (CRM), Montreal, QC, Canada.
Murphy, S. A., Laber, E., Nahum-Shani, I., & Pelham, W. (2011, April). Using data to inform sequential, individualized clinical decision making. In L. M. Collins (Chair), Drawing on ideas from engineering and computer science to build better behavioral interventions. Symposium presented at the Society of Behavioral Medicine Annual Meeting & Scientific Sessions, Washington, DC.
Almirall, D., Compton, S. N., & Murphy, S. A. (2011, April). Experimental designs for developing adaptive treatment strategies. Preconference workshop presented at the Society of Behavioral Medicine Annual Meeting & Scientific Sessions, Washington, DC.
Lizotte, D. J., Bowling, M., & Murphy, S. A. (2010, October). Inverse preference elicitation for dynamic treatment regimes. Poster presented at the Society for Medical Decision Making 2010 Meeting.
Laber, E., & Murphy, S. A. (2010, October). Inference for dynamic treatment regimens. Presented at Department of Mathematics and Statistics, Texas Tech University, Lubbock, TX.Department of Statistics, Colorado State University, Fort Collins, CO. Michigan State University, Lansing, MI.
Almirall, D., McCaffrey, D. F., Griffin, B. A., & Murphy, S. A. (2010, August). Time-varying causal effect moderation in the presence of time-varying confounding using structural nested mean models. Presented at the Joint Statistical Meetings, Vancouver, Canada.
Laber, E., & Murphy, S. A. (2010, July). Adaptive confidence intervals for the test error in classification. Presented at the High-Dimensional Models and Processes Conference, Seattle, WA.
Almirall, D., Compton, S. N., & Murphy, S. A. (2010, June). Experimental designs for developing adaptive treatment strategies: With application to the management of bipolar disorder. Presented at the International College of Neuro-Psychopharmacology (CINP) Congress, Hong Kong, China.
Laber, E. B., Qian, M., Nahum-Shani, I., & Murphy, S. A. (2010, January). Constructing dynamic treatment regimes. Presented at the International Conference on Health Policy and Statistics, Washington, D.C.
Murphy, S. A., & Almirall, D. (2011, April). Getting SMART about developing individualized sequences of health intervention. Seminar presented at the Society of Behavioral Medicine Annual Meeting & Scientific Sessions, Washington, DC.
Software
PROC QLEARN (Version 1.0) [Software] (2012). University Park: The Methodology Center, Penn State. Retrieved from http://methodology.psu.edu
Ertefaie, A., Almirall, D. A., Huang L., Dziak, J. J., Wagner, A. T., & Murphy, S. A. (2012). SAS PROC QLEARN users’ guide (Version 1.0). University Park: The Methodology Center, Penn State. Retrieved from http://methodology.psu.edu