mr_grip: MR-GRIP: a modified MR-Egger model with the Genotype Recoding...

In autoMR: Automated Mendelian Randomization Workflows and Visualizations

MR-GRIP: a modified MR-Egger model with the Genotype Recoding Invariance Property

Description

Implements the modified MR-Egger model with the Genotype Recoding Invariance Property (MR-GRIP) due to Dudbridge and Bowden et al. (2025). The model multiplies each term of MR-Egger by the genotype-phenotype association, making results invariant to allele coding. The parameters argument is accepted for API compatibility but is not used; all weights and computations follow the original GRIP specification exactly.

Usage

mr_grip(b_exp, b_out, se_exp, se_out, parameters)

Arguments

b_exp	Vector of genetic effects on exposure.
b_out	Vector of genetic effects on outcome.
se_exp	Standard errors of genetic effects on exposure.
se_out	Standard errors of genetic effects on outcome.
parameters	Unused; accepted for API compatibility only.

Value

List with elements: b, se, pval (causal estimate, SE, p-value); b_i, se_i, pval_i (intercept and its SE and p-value); b.adj, se.adj, pval.adj (weak-instrument-adjusted estimate); nsnp, mod, smod, dat.

autoMR documentation built on June 12, 2026, 9:07 a.m.