Controlling Selection Bias in Causal Inference

Elias Bareinboim, Judea Pearl
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:100-108, 2012.

Abstract

Selection bias, caused by preferential exclusion of samples from the data, is a major obstacle to valid causal and statistical inferences; it cannot be removed by randomized experiments and can hardly be detected in either experimental or observational studies. This paper highlights several graphical and algebraic methods capable of mitigating and sometimes eliminating this bias. These nonparametric methods generalize previously reported results, and identify the type of knowledge that is needed for reasoning in the presence of selection bias. Specifically, we derive a general condition together with a procedure for deciding recoverability of the odds ratio (OR) from s-biased data. We show that recoverability is feasible if and only if our condition holds. We further offer a new method of controlling selection bias using instrumental variables that permits the recovery of other effect measures besides OR.

Cite this Paper


BibTeX
@InProceedings{pmlr-v22-bareinboim12, title = {Controlling Selection Bias in Causal Inference}, author = {Bareinboim, Elias and Pearl, Judea}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics}, pages = {100--108}, year = {2012}, editor = {Lawrence, Neil D. and Girolami, Mark}, volume = {22}, series = {Proceedings of Machine Learning Research}, address = {La Palma, Canary Islands}, month = {21--23 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v22/bareinboim12/bareinboim12.pdf}, url = {https://proceedings.mlr.press/v22/bareinboim12.html}, abstract = {Selection bias, caused by preferential exclusion of samples from the data, is a major obstacle to valid causal and statistical inferences; it cannot be removed by randomized experiments and can hardly be detected in either experimental or observational studies. This paper highlights several graphical and algebraic methods capable of mitigating and sometimes eliminating this bias. These nonparametric methods generalize previously reported results, and identify the type of knowledge that is needed for reasoning in the presence of selection bias. Specifically, we derive a general condition together with a procedure for deciding recoverability of the odds ratio (OR) from s-biased data. We show that recoverability is feasible if and only if our condition holds. We further offer a new method of controlling selection bias using instrumental variables that permits the recovery of other effect measures besides OR.} }
Endnote
%0 Conference Paper %T Controlling Selection Bias in Causal Inference %A Elias Bareinboim %A Judea Pearl %B Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2012 %E Neil D. Lawrence %E Mark Girolami %F pmlr-v22-bareinboim12 %I PMLR %P 100--108 %U https://proceedings.mlr.press/v22/bareinboim12.html %V 22 %X Selection bias, caused by preferential exclusion of samples from the data, is a major obstacle to valid causal and statistical inferences; it cannot be removed by randomized experiments and can hardly be detected in either experimental or observational studies. This paper highlights several graphical and algebraic methods capable of mitigating and sometimes eliminating this bias. These nonparametric methods generalize previously reported results, and identify the type of knowledge that is needed for reasoning in the presence of selection bias. Specifically, we derive a general condition together with a procedure for deciding recoverability of the odds ratio (OR) from s-biased data. We show that recoverability is feasible if and only if our condition holds. We further offer a new method of controlling selection bias using instrumental variables that permits the recovery of other effect measures besides OR.
RIS
TY - CPAPER TI - Controlling Selection Bias in Causal Inference AU - Elias Bareinboim AU - Judea Pearl BT - Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics DA - 2012/03/21 ED - Neil D. Lawrence ED - Mark Girolami ID - pmlr-v22-bareinboim12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 22 SP - 100 EP - 108 L1 - http://proceedings.mlr.press/v22/bareinboim12/bareinboim12.pdf UR - https://proceedings.mlr.press/v22/bareinboim12.html AB - Selection bias, caused by preferential exclusion of samples from the data, is a major obstacle to valid causal and statistical inferences; it cannot be removed by randomized experiments and can hardly be detected in either experimental or observational studies. This paper highlights several graphical and algebraic methods capable of mitigating and sometimes eliminating this bias. These nonparametric methods generalize previously reported results, and identify the type of knowledge that is needed for reasoning in the presence of selection bias. Specifically, we derive a general condition together with a procedure for deciding recoverability of the odds ratio (OR) from s-biased data. We show that recoverability is feasible if and only if our condition holds. We further offer a new method of controlling selection bias using instrumental variables that permits the recovery of other effect measures besides OR. ER -
APA
Bareinboim, E. & Pearl, J.. (2012). Controlling Selection Bias in Causal Inference. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 22:100-108 Available from https://proceedings.mlr.press/v22/bareinboim12.html.

Related Material