Unobservable Selection and Coefficient Stability

Implementation of: "Unobservable selection and coefficient stability: Theory and evidence.", Oster E, JBES 37.2 (2019)
22 Downloads
Updated 4 Feb 2020

View License

The function implements the method of (*) for evaluating robustness to omitted variable bias.
Specifically, it implements Proposition 2, Corollary 1 and Proposition 3. The implementation relies upon Matlab's fitlm(). Examples included for both computing the (a) bias-adjusted treatment
effect and (b) the delta value (bound) to match a given treatment effect, for the unrestricted estimator under additional (unrelated) controls. The complete documentation is within the function oster.mat.

(*) Oster, Emily. "Unobservable selection and coefficient stability: Theory and evidence." Journal of Business & Economic Statistics 37.2 (2019): 187-204.

Cite As

Martin Magris (2026). Unobservable Selection and Coefficient Stability (https://nl.mathworks.com/matlabcentral/fileexchange/74137-unobservable-selection-and-coefficient-stability), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2019b
Compatible with any release
Platform Compatibility
Windows macOS Linux
Categories
Find more on Verification, Validation, and Test in Help Center and MATLAB Answers
Version Published Release Notes
1.0.0