An absolute measure of heterogeneity for lnOR in meta-analysis
Abstract
Quantifying the heterogeneity is an important issue in meta-analysis. The conventional heterogeneity statistic, I2, heavily depends on study sample sizes and tends to approach one as the sample sizes increase. To overcome this limitation, a sample size independent measure, ICCMA, has recently been developed to quantify the heterogeneity, yet this method is restricted to meta-analysis with continuous outcomes. In practice, however, binary outcomes are more widely encountered, with the log odds ratio (lnOR) frequently adopted as an effect size to compare the effects of two treatments in terms of odds. To fill the gap, we propose a new heterogeneity measure for meta-analysis with binary outcomes by introducing a latent continuous variable model. Under this framework, the proposed measure admits a closed-form expression within the random-effects meta-analysis model with lnOR as the effect size. We define this sample size independent measure as ICCMAOR, and moreover propose a new estimator, I2A, to evaluate this measure. Simulation studies demonstrate that our new estimator is nearly unbiased and aligns closely with its counterpart applied for standardized mean differences when the continuous variable is observable. A real data application further demonstrates that the proposed heterogeneity statistic for binary outcomes and its counterpart for continuous outcomes provide interpretable and coherent estimates across different outcome types.
Related
- Geology-Aware Multiscale Fractal Coupling Graphs for Cross-Well Heterogeneity Characterization of Coal-Measure Well Logs in the Eastern Ordos Basin
- Design-Indexed Heterogeneity in Meta-Analysis: A Constrained Location-Scale Specification
- Infinite free pro-p products as absolute Galois groups
- Iterative Methods for Solving New Generalized Absolute Value Equations
- Bad(r;s) is Hyperplane Absolute Winning
BibTeX
@misc{yang2026absolute,
title = {{An absolute measure of heterogeneity for lnOR in meta-analysis}},
author = {Ke Yang and Lei Shi and Wangli Xu and Liping Zhu and Tiejun Tong},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.19211},
eprint = {2609.19211},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.19211},
}
RIS
TY - UNPB
TI - An absolute measure of heterogeneity for lnOR in meta-analysis
AU - Ke Yang
AU - Lei Shi
AU - Wangli Xu
AU - Liping Zhu
AU - Tiejun Tong
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.19211
UR - https://arxiv.org/abs/2609.19211
AB - Quantifying the heterogeneity is an important issue in meta-analysis. The conventional heterogeneity statistic, I^2, heavily depends on study sample sizes and tends to approach one as the sample sizes increase. To overcome this limitation, a sample size independent measure, ICC_MA, has recently been developed to quantify the heterogeneity, yet this method is restricted to meta-analysis with continuous outcomes. In practice, however, binary outcomes are more widely encountered, with the log odds ratio (lnOR) frequently adopted as an effect size to compare the effects of two treatments in terms of odds. To fill the gap, we propose a new heterogeneity measure for meta-analysis with binary outcomes by introducing a latent continuous variable model. Under this framework, the proposed measure admits a closed-form expression within the random-effects meta-analysis model with lnOR as the effect size. We define this sample size independent measure as ICC_MA^OR, and moreover propose a new estimator, I^2_A, to evaluate this measure. Simulation studies demonstrate that our new estimator is nearly unbiased and aligns closely with its counterpart applied for standardized mean differences when the continuous variable is observable. A real data application further demonstrates that the proposed heterogeneity statistic for binary outcomes and its counterpart for continuous outcomes provide interpretable and coherent estimates across different outcome types.
ER -