Empirical economics papers report standard errors to take into account uncertainty associated with sampling variation but rarely consider non-sampling variation from researcher choices about measurement of key variables, functional form choice, identification strategy, and data set. In this paper, we review the literature on alternative methods for taking account of non-sampling variability, develop a typology of sources of non-sampling variation, and conduct an empirical exercise in which we estimate the relative and absolute importance of different types of non-sampling variation. The empirical exercise proceeds in the context of the literature that seeks to estimate the causal effect of college quality on educational and labor market outcomes.
Date
30.8.2023
, 1:00 pm to 2:30 pm
Speaker
Jeffrey Smith
University of Wisconsin-Madison
Jeffrey Smith is Paul T. Heyne Distinguished Chair in Economics and Richard Meese Chair in Applied Econometrics at the University of Wisconsin-Madison, Associate Director for Research and Teaching of the Institute for Research on Poverty, and a Fellow of the Society of Labor Economists. He received his Ph.D. in Economics from the University of Chicago in 1996 and taught at the University of Western Ontario, the University of Maryland and the University of Michigan prior to coming to Wisconsin in January 2018. His research centers on experimental and non-experimental methods for the evaluation of interventions, with particular application to social and educational programs. He has published papers on many aspects of the evaluation and operation of active labor market programs, along with papers examining the labor market effects of university quality, teacher value-added in developing countries, and the use of statistical treatment rules to assign persons to government programs.