Carlos Cinelli is an assistant professor at the Department of Statistics at the University of Washington. He is also a data science fellow in the eScience Institute, and affiliate faculty at the Center for Statistics and the Social Sciences. His research focuses on developing causal and statistical methods for transparent and robust causal claims in the empirical sciences. He is particularly interested in the inferential challenges faced by social and health scientists, as well as the intersections of causality with machine learning and artificial intelligence.
Talk: Long Story Short: Omitted Variable Bias in Causal Machine Learning
Abstract: We develop a general theory of omitted variable bias for a wide range of common causal parameters, including (but not limited to) averages of potential outcomes, average treatment effects, average causal derivatives, and policy effects from covariate shifts. Our theory applies to nonparametric models, while naturally allowing for (semi-)parametric restrictions (such as partial linearity) when such assumptions are made. We show how simple plausibility judgments on the maximum explanatory power of omitted variables are sufficient to bound the magnitude of the bias, thus facilitating sensitivity analysis in otherwise complex, nonlinear models. Finally, we provide flexible and efficient statistical inference methods for the bounds, which can leverage modern machine learning algorithms for estimation. These results allow empirical researchers to perform sensitivity analyses in a flexible class of machine-learned causal models using very simple, and interpretable, tools. We demonstrate the utility of our approach with two empirical examples.