On relations between the Cochran--Mantel--Haenszel test and Augmented Inverse Probability Weighting
Abstract
This note revisits the Cochran-Mantel-Haenszel (CMH) test in light of the increasing use of causal inference methods in clinical trials. It shows that the CMH test statistic can be interpreted as a standardized version of the augmented inverse probability weighted (AIPW) estimate of the causal average treatment effect. Consequently, it is not restricted to an interpretation as a test of the common-odds ratio in a stratified logistic regression model. The note then discusses conditional and unconditional variances for this estimator as well as variance estimation and its implications for testing. The results clarify the relationship between the classical conditional CMH test and Wald-type AIPW tests, and show that, under equal treatment allocation, the CMH test is asymptotically conservative for the weak null hypothesis of zero average treatment effect. %This note revisits the Cochran--Mantel--Haenszel (CMH) test in light of the increasing use of causal inference methods in clinical trials. For stratified randomized trials with binary endpoints and a common treatment allocation fraction across strata, we show that the numerator of the CMH statistic is proportional to an augmented inverse probability weighted estimator of the population-average causal risk difference. This provides an interpretation of the CMH test that does not depend on the common-odds-ratio model often used to motivate it. We then compare conditional and unconditional variance concepts for this estimator and discuss their implications for testing. The results clarify the relationship between the classical conditional CMH test and Wald-type AIPW tests, and show that, under equal treatment allocation, the CMH test is asymptotically conservative for the weak null hypothesis of zero average treatment effect.
Related
- Keeping Score: Adaptive, Tuning-Free Loss Weighting for Score-Augmented Neural Ratio Estimation
- Re-randomization-probability weighting for population-adjusted comparisons of maintenance outcomes across trial designs
- Inverse probability weighting-based mediation analysis for microbiome data
- Approximate Gromov--Hausdorff continuity of magnitude and weighting
- Co-sufficient weighting: leveraging sparsity for more powerful variable selection in the linear model
BibTeX
@misc{glimm2026relations,
title = {{On relations between the Cochran--Mantel--Haenszel test and Augmented Inverse Probability Weighting}},
author = {Ekkehard Glimm},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.01362},
eprint = {2610.01362},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.01362},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - On relations between the Cochran--Mantel--Haenszel test and Augmented Inverse Probability Weighting
AU - Ekkehard Glimm
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.01362
UR - https://arxiv.org/abs/2610.01362
AB - This note revisits the Cochran-Mantel-Haenszel (CMH) test in light of the increasing use of causal inference methods in clinical trials. It shows that the CMH test statistic can be interpreted as a standardized version of the augmented inverse probability weighted (AIPW) estimate of the causal average treatment effect. Consequently, it is not restricted to an interpretation as a test of the common-odds ratio in a stratified logistic regression model. The note then discusses conditional and unconditional variances for this estimator as well as variance estimation and its implications for testing. The results clarify the relationship between the classical conditional CMH test and Wald-type AIPW tests, and show that, under equal treatment allocation, the CMH test is asymptotically conservative for the weak null hypothesis of zero average treatment effect. %This note revisits the Cochran--Mantel--Haenszel (CMH) test in light of the increasing use of causal inference methods in clinical trials. For stratified randomized trials with binary endpoints and a common treatment allocation fraction across strata, we show that the numerator of the CMH statistic is proportional to an augmented inverse probability weighted estimator of the population-average causal risk difference. This provides an interpretation of the CMH test that does not depend on the common-odds-ratio model often used to motivate it. We then compare conditional and unconditional variance concepts for this estimator and discuss their implications for testing. The results clarify the relationship between the classical conditional CMH test and Wald-type AIPW tests, and show that, under equal treatment allocation, the CMH test is asymptotically conservative for the weak null hypothesis of zero average treatment effect.
ER -