The INSIDE assumption under all positive coding: interpretation and partial empirical assessment
Abstract
Mendelian randomisation (MR) implemented through instrumental variable (IV) analysis is a popular strategy for strengthening causal inference in observational studies. A key assumption for several MR estimators, including MR-Egger regression, is the INstrument Strength Independent of Direct Effect (INSIDE) assumption. However, there is no established empirical test for assessing the plausibility of this assumption. Moreover, INSIDE depends on how genetic variants are coded (i.e., on the choice of the effect allele), which is often arbitrary and therefore hampers assessing the plausibility of this assumption on substantive grounds. In this paper, we show that the all-positive coding scheme (i.e., for all variants, choosing the allele positively associated with the exposure as the effect allele), which is typically used in MR-Egger, is equivalent to a coding-invariant model that can be given a natural interpretation because the direct effect parameters under this coding scheme are in the same direction as the bias of individual-variant ratio estimators. Moreover, using both theoretical arguments and simulations, we show that, under commonly assumed data-generating models in the MR methodological literature, heteroscedasticity of instrument-outcome coefficients according to instrument-exposure coefficients is a feature of at least some types of INSIDE violation, indicating that heteroscedasticity tests could contribute to assessing the plausibility of the INSIDE assumption. We further highlight specific cases where the test would not work. We illustrate its application by re-analysing a real dataset assessing the causal effect of large particle high density lipoprotein cholesterol on age-related macular degeneration.
Related
- A Flexible Heavy-Tailed Probability Model for Skewed Positive Data: Theory, Estimation, and Empirical Assessment
- A Sklar-Type Decomposition for Positive Binary Distributions and a Gibbs Interpretation
- Empirical-Bayes spectral partial pooling across related tasks
- Partial AUC Maximization from Positive-unlabeled Data
- Natural coordinates for constrained correlation functions: Partial autocorrelations and the geometry of positive power spectra
BibTeX
@misc{hartwig2026inside,
title = {{The INSIDE assumption under all positive coding: interpretation and partial empirical assessment}},
author = {Fernando Pires Hartwig and George Davey Smith and Frank Dudbridge and Jack Bowden},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.37347},
eprint = {2609.37347},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.37347},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - The INSIDE assumption under all positive coding: interpretation and partial empirical assessment
AU - Fernando Pires Hartwig
AU - George Davey Smith
AU - Frank Dudbridge
AU - Jack Bowden
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.37347
UR - https://arxiv.org/abs/2609.37347
AB - Mendelian randomisation (MR) implemented through instrumental variable (IV) analysis is a popular strategy for strengthening causal inference in observational studies. A key assumption for several MR estimators, including MR-Egger regression, is the INstrument Strength Independent of Direct Effect (INSIDE) assumption. However, there is no established empirical test for assessing the plausibility of this assumption. Moreover, INSIDE depends on how genetic variants are coded (i.e., on the choice of the effect allele), which is often arbitrary and therefore hampers assessing the plausibility of this assumption on substantive grounds. In this paper, we show that the all-positive coding scheme (i.e., for all variants, choosing the allele positively associated with the exposure as the effect allele), which is typically used in MR-Egger, is equivalent to a coding-invariant model that can be given a natural interpretation because the direct effect parameters under this coding scheme are in the same direction as the bias of individual-variant ratio estimators. Moreover, using both theoretical arguments and simulations, we show that, under commonly assumed data-generating models in the MR methodological literature, heteroscedasticity of instrument-outcome coefficients according to instrument-exposure coefficients is a feature of at least some types of INSIDE violation, indicating that heteroscedasticity tests could contribute to assessing the plausibility of the INSIDE assumption. We further highlight specific cases where the test would not work. We illustrate its application by re-analysing a real dataset assessing the causal effect of large particle high density lipoprotein cholesterol on age-related macular degeneration.
ER -