A robustness test for estimating total effects with covariate adjustment

Zehao Su, Leonard Henckel
Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, PMLR 180:1886-1895, 2022.

Abstract

Suppose we want to estimate a total effect with covariate adjustment in a linear structural equation model. We have a causal graph to decide what covariates to adjust for, but are uncertain about the graph. Here, we propose a testing procedure, that exploits the fact that there are multiple valid adjustment sets for the target total effect in the causal graph, to perform a robustness check on the graph. If the test rejects, it is a strong indication that we should not rely on the graph. We discuss what mistakes in the graph our testing procedure can detect and which ones it cannot and develop two strategies on how to select a list of valid adjustment sets for the procedure. We also connect our result to the related econometrics literature on coefficient stability tests.

Cite this Paper

BibTeX
@InProceedings{pmlr-v180-su22a, title = {A robustness test for estimating total effects with covariate adjustment}, author = {Su, Zehao and Henckel, Leonard}, booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence}, pages = {1886--1895}, year = {2022}, editor = {Cussens, James and Zhang, Kun}, volume = {180}, series = {Proceedings of Machine Learning Research}, month = {01--05 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v180/su22a/su22a.pdf}, url = {https://proceedings.mlr.press/v180/su22a.html}, abstract = {Suppose we want to estimate a total effect with covariate adjustment in a linear structural equation model. We have a causal graph to decide what covariates to adjust for, but are uncertain about the graph. Here, we propose a testing procedure, that exploits the fact that there are multiple valid adjustment sets for the target total effect in the causal graph, to perform a robustness check on the graph. If the test rejects, it is a strong indication that we should not rely on the graph. We discuss what mistakes in the graph our testing procedure can detect and which ones it cannot and develop two strategies on how to select a list of valid adjustment sets for the procedure. We also connect our result to the related econometrics literature on coefficient stability tests.} }
Endnote
%0 Conference Paper %T A robustness test for estimating total effects with covariate adjustment %A Zehao Su %A Leonard Henckel %B Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2022 %E James Cussens %E Kun Zhang %F pmlr-v180-su22a %I PMLR %P 1886--1895 %U https://proceedings.mlr.press/v180/su22a.html %V 180 %X Suppose we want to estimate a total effect with covariate adjustment in a linear structural equation model. We have a causal graph to decide what covariates to adjust for, but are uncertain about the graph. Here, we propose a testing procedure, that exploits the fact that there are multiple valid adjustment sets for the target total effect in the causal graph, to perform a robustness check on the graph. If the test rejects, it is a strong indication that we should not rely on the graph. We discuss what mistakes in the graph our testing procedure can detect and which ones it cannot and develop two strategies on how to select a list of valid adjustment sets for the procedure. We also connect our result to the related econometrics literature on coefficient stability tests.
APA
Su, Z. & Henckel, L.. (2022). A robustness test for estimating total effects with covariate adjustment. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 180:1886-1895 Available from https://proceedings.mlr.press/v180/su22a.html.

Related Material