Unobservable Selection and Coefficient Stability: Theory and Evidence Article Swipe

View

Related Concepts

unobservable bounding overwatch robustness (evolution) extension (predicate logic) observable selection (genetic algorithm) econometrics stability (learning theory) mathematics mathematical economics computer science artificial intelligence chemistry programming language machine learning biochemistry gene quantum mechanics physics

Emily Oster ·

YOU? · · 2016 · Open Access · · DOI: https://doi.org/10.1080/07350015.2016.1227711 · OA: W2465587637

A common approach to evaluating robustness to omitted variable bias is to observe coefficient movements after inclusion of controls. This is informative only if selection on observables is informative about selection on unobservables. Although this link is known in theory in existing literature, very few empirical articles approach this formally. I develop an extension of the theory that connects bias explicitly to coefficient stability. I show that it is necessary to take into account coefficient and <i>R</i>-squared movements. I develop a formal bounding argument. I show two validation exercises and discuss application to the economics literature. Supplementary materials for this article are available online.