Professional Biography

Dr. Wendy Chan is an Assistant Professor of Education in the Human Development and Quantitative Methods Division at Penn GSE. She received her Ph.D. in statistics from Northwestern University, where she was a graduate research assistant for the Institute for Policy Research. She began her career in education as a member of Teach for America, where she taught sixth- and eighth-grade mathematics in a large middle school in New York City. Her work has appeared in Evaluation Review and Communications for Statistical Applications and Methods.

Research Interests and Current Projects

Dr. Chan specializes in applied educational statistics, and her research projects and interests are at the leading edge of work on statistics methods in field contexts, including scaling up interventions. Her dissertation, Extensions to the Generalizability of Experiments in the Social Sciences, was about the intellectual and statistical challenges of generalizing the results of localized randomized trials to larger populations. Specifically, it focused on applications of partial identification and small area estimation methods to estimation of population average treatment effects in the absence of equal probability sampling. With partial identification, her work examines the role of alternative assumptions to strong ignorability of sample selection in making inferences on population parameters. With small area estimation, Dr. Chan’s work considers use of small area models in improving the precision of estimators when there is limited sample size. Aside from her work on generalization, Dr. Chan’s research has ventured into power analyses and analyzed the extent to which analogies in design parameters can be made.

She is currently working on two projects. The first considers the role of stratification on improving the precision of bounds for generalization. The second looks at compositional differences in populations of inference and the implications for generalizations over time.


Ph.D. (Statistics) Northwestern University, 2016

M.A. (Mathematics Education) Lehman College, City University of New York, 2010

B.A. (Economics and Mathematics) Barnard College, Columbia University, 2008

Areas of Expertise

Statistical methods to improve generalizations in education

Partial identification methods with applications to the social sciences

Multilevel modeling and experimental design

Propensity score methods for generalization

Small area estimation


Chan, W. (2018). Applications of small area estimation to generalization with subclassification by propensity scores. Journal of Educational and Behavioral Statistics43(2), 182–224.

Chan, W. (2017). Partially identified treatment effects for generalizability. Journal of Research on Educational Effectiveness10(3), 646–669.

Tipton, E., Hallberg, K., Hedges, L. V., and Chan, W. (2016). Implications of small samples for generalization: Adjustments and rules of thumb. Evaluation Review (Special Issue: External Validity 2), 41(5), 472–505.

Kang, J., Chan, W., Kim, M. O., & Steiner, P. M. (2016). Practice of causal inference with the propensity of being zero or one: Assessing the effect of arbitrary cutoffs of propensity scores. Communications for Statistical Applications and Methods, 23(1), 1–20.