Claude Messan Setodji

claude setodji, s0555
Co-Director, RAND Center for Causal Inference; Senior Statistician; Professor, Pardee RAND Graduate School
Pittsburgh Office


Ph.D. in statistics, University of Minnesota


Claude Messan Setodji is a senior statistician at the RAND Corporation, codirector of the RAND Center for Causal Inference, and a professor at the Pardee RAND Graduate School. His research interests include applications of statistics to public policy, especially in health care cost and care, causal inferences, sampling techniques, and data reduction and visualization. Setodji's current work focuses on improved quantitative methods in health and child development quality assessments and the development of statistical methods for inference on ecological momentary assessment of health and behavior intention outcomes. He is currently working on causal inference propensity score methods in the presence of measurement errors in covariates. He recently led RAND projects including the evaluation of the redesign of the Nationwide Inpatient Sample and the development of small area estimation cost-effective and statistically reliable approaches for deriving estimates of the prevalence of various health risk behaviors, risk factors, and outcomes in small racial, ethnic, and other hard-to-reach populations in the U.S. Setodji also has interests in international education and health care policy. Setodji earned his Ph.D. in statistics from the University of Minnesota.

Recent Projects

  • Identifying Threshold Levels of Structural and Process Quality
  • Consumer Assessment of Healthcare Providers and Systems CAHPS IV
  • Evaluation, Development and Utilization of Statistical and Mathematical Methods
  • Assessment of Advertising on smoking behavior
  • Evaluation of Federally Qualified Health Center Demonstration

Selected Publications

Setodji C.M., McCaffrey D.F., Burgette L.F., Almirall D., and Griffin B.A., "The right tool for the job: choosing between covariate balancing and generalized boosted model propensity scores," Epidemiology, 2017 (forthcoming)

Setodji C.M., Le, V. and Schaack D., "Using generalized additive modeling to empirically identify thresholds within the ITERS in relation to toddlers' cognitive development.," Developmental Psychology, 49(4):632-645, 2013 (forthcoming)

Setodji C.M., Elliott M.N., Abel G., Burt J., Roland M., Campbell J., "Evaluating Differential Item Functioning in the English General Practice Patient Survey: Comparison of South Asian and White British Subgroups.," Medical Care, 53(9):809-817, 2015

Robbins M.W. and Setodji C.M., "Causal inference using mixture models: a word of caution.," Medical care, 52(9):770-772, 2014

Setodji C.M., Martino S.C., Scharf D., and Shadel W. G., "Quantifying the persistence of pro-smoking media effects on college students' smoking risk," Journal of Adolescent Health, 54:474-480, 2014

Setodji C.M., Scheuner M., Pankow J.S., Blumenthal R.S., Chen H. and Keeler E., "A graphical method for assessing risk factor threshold values using the generalized additive model: The Multi-Ethnic Study of Atherosclerosis.," Health Services and Outcomes Research Methodology, 12:62-79, 2012

Setodji C.M., Le, V. and Schaack D., "Accounting for Movement between Childcare Classrooms: Does it Change Interpretations of Teacher Effects?" Applied Developmental Psychology, 33(1):1-12, 2012

Cook, R.D. and Setodji, M.C., "A model-free test for reduced ranked in multivariate Regression," Journal of the American statistical association, 98:340-351, 2002