Assessing the Confounding Effects of Unobserved Factors
This topic equips students with tools to assess the effects unobserved factors have on the dependent variable in question, in order to isolate the causal effect of the observed factors.
Topic Learning Outcome: Students will understand the distinction between "observed factors" and "unobserved factors" that can influence a dependent variable of interest and be able to apply this knowledge in the context of efforts to assess the effectiveness of policy interventions.
Core Concepts associated with this Topic: Evaluability; Single Difference (in impact evaluation).
Harvard University: API-208 Program Evaluation: Estimating Program Effectiveness with Empirical Analysis
Rosenbaum, P.R. (2005), "Sensitivity Analysis in Observational Studies," Encyclopedia of Statistics in Behavioral Science, vol. 4, 1809-1814.
Imbens, G.W. (2003), "Sensitivity to Exogeneity Assumptions in Program Evaluation," American Economic Review (Papers & Proceedings), vol. 93(2), 126-132.
Rosenbaum, P.R. (2002), Observational Studies. New York: Springer-Verlag. Chapter 4.
Rosenbaum, P.R. and D.B. Rubin (1983), "Assessing Sensitivity to an Unobserved Binary Covariate in an Observational Study with Binary Outcome," Journal of the Royal Statistical Society. Series B, vol. 45(2), 212-218.
Sample Assessment Questions:
1.) Identify one program, policy or government activity that is particularly difficult to evaluate in terms of efficiency and effectiveness. In a 3-5 page short paper, describe the evaluation challenges involved and identify some possible strategies to overcome those challenges and evaluate the program/policy/activity in question.
Page created by Sean Goertzen and Ben Eisen on 21 May 2015.