Statistical test for consistent estimation of causal effects in linear non-Gaussian models

Doris Entner, Patrik Hoyer, Peter Spirtes
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:364-372, 2012.

Abstract

In many fields of science researchers are faced with the problem of estimating causal effects from non-experimental data. A key issue is to avoid inconsistent estimators due to confounding by measured or unmeasured covariates, a problem commonly solved by ’adjusting for’ a subset of the observed variables. When the data generating process can be represented by a directed acyclic graph, and this graph structure is known, there exist simple graphical procedures for determining which subset of covariates should be adjusted for to obtain consistent estimators of the causal effects. However, when the graph is not known no general and complete procedures for this task are available. In this paper we introduce such a method for linear non-Gaussian models, requiring only partial knowledge about the temporal ordering of the variables: We provide a simple statistical test for inferring whether an estimator of a causal effect is consistent when controlling for a subset of measured covariates, and we present heuristics to search for such a set. We show empirically that this statistical test identifies consistent vs inconsistent estimates, and that the search heuristics outperform the naive approach of adjusting for all observed covariates.

Cite this Paper

BibTeX
@InProceedings{pmlr-v22-entner12, title = {Statistical test for consistent estimation of causal effects in linear non-Gaussian models}, author = {Entner, Doris and Hoyer, Patrik and Spirtes, Peter}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics}, pages = {364--372}, 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/entner12/entner12.pdf}, url = {https://proceedings.mlr.press/v22/entner12.html}, abstract = {In many fields of science researchers are faced with the problem of estimating causal effects from non-experimental data. A key issue is to avoid inconsistent estimators due to confounding by measured or unmeasured covariates, a problem commonly solved by ’adjusting for’ a subset of the observed variables. When the data generating process can be represented by a directed acyclic graph, and this graph structure is known, there exist simple graphical procedures for determining which subset of covariates should be adjusted for to obtain consistent estimators of the causal effects. However, when the graph is not known no general and complete procedures for this task are available. In this paper we introduce such a method for linear non-Gaussian models, requiring only partial knowledge about the temporal ordering of the variables: We provide a simple statistical test for inferring whether an estimator of a causal effect is consistent when controlling for a subset of measured covariates, and we present heuristics to search for such a set. We show empirically that this statistical test identifies consistent vs inconsistent estimates, and that the search heuristics outperform the naive approach of adjusting for all observed covariates.} }
Endnote
%0 Conference Paper %T Statistical test for consistent estimation of causal effects in linear non-Gaussian models %A Doris Entner %A Patrik Hoyer %A Peter Spirtes %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-entner12 %I PMLR %P 364--372 %U https://proceedings.mlr.press/v22/entner12.html %V 22 %X In many fields of science researchers are faced with the problem of estimating causal effects from non-experimental data. A key issue is to avoid inconsistent estimators due to confounding by measured or unmeasured covariates, a problem commonly solved by ’adjusting for’ a subset of the observed variables. When the data generating process can be represented by a directed acyclic graph, and this graph structure is known, there exist simple graphical procedures for determining which subset of covariates should be adjusted for to obtain consistent estimators of the causal effects. However, when the graph is not known no general and complete procedures for this task are available. In this paper we introduce such a method for linear non-Gaussian models, requiring only partial knowledge about the temporal ordering of the variables: We provide a simple statistical test for inferring whether an estimator of a causal effect is consistent when controlling for a subset of measured covariates, and we present heuristics to search for such a set. We show empirically that this statistical test identifies consistent vs inconsistent estimates, and that the search heuristics outperform the naive approach of adjusting for all observed covariates.
RIS
TY - CPAPER TI - Statistical test for consistent estimation of causal effects in linear non-Gaussian models AU - Doris Entner AU - Patrik Hoyer AU - Peter Spirtes 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-entner12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 22 SP - 364 EP - 372 L1 - http://proceedings.mlr.press/v22/entner12/entner12.pdf UR - https://proceedings.mlr.press/v22/entner12.html AB - In many fields of science researchers are faced with the problem of estimating causal effects from non-experimental data. A key issue is to avoid inconsistent estimators due to confounding by measured or unmeasured covariates, a problem commonly solved by ’adjusting for’ a subset of the observed variables. When the data generating process can be represented by a directed acyclic graph, and this graph structure is known, there exist simple graphical procedures for determining which subset of covariates should be adjusted for to obtain consistent estimators of the causal effects. However, when the graph is not known no general and complete procedures for this task are available. In this paper we introduce such a method for linear non-Gaussian models, requiring only partial knowledge about the temporal ordering of the variables: We provide a simple statistical test for inferring whether an estimator of a causal effect is consistent when controlling for a subset of measured covariates, and we present heuristics to search for such a set. We show empirically that this statistical test identifies consistent vs inconsistent estimates, and that the search heuristics outperform the naive approach of adjusting for all observed covariates. ER -
APA
Entner, D., Hoyer, P. & Spirtes, P.. (2012). Statistical test for consistent estimation of causal effects in linear non-Gaussian models. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 22:364-372 Available from https://proceedings.mlr.press/v22/entner12.html.

Related Material