Maya B. Mathur · Stanford University

Software

Last updated Apr 2026

Web interfaces

3 tools
Screenshot of metabias.io
metabias.io

metabias.io

Sensitivity analyses for publication bias, p-hacking, unmeasured confounding, and their joint effects in meta-analyses. Point-and-click interface that produces publication-ready output.

Screenshot of E-value calculator
evalue-calculator.com

E-value calculator

Sensitivity analyses for unmeasured confounding in observational studies. Computes E-values and confidence-interval-based bounds for a range of effect measures.

Screenshot of E-values for meta-analyses
evalue-calculator.com/meta

E-values for meta-analyses

Sensitivity analyses for unmeasured confounding in meta-analyses. Complements the core E-value calculator with meta-analytic extensions.

R packages

12 packages
R package miapack
Multiple imputation for missing-not-at-random data with incomplete auxiliary variables. Implements the methods from Mathur, Seaman, Zhang, McGrath & Shpitser.
With McGrath, Mathur
R package multibiasmeta
Corrections and sensitivity analyses for within-study and across-study biases in meta-analyses.
With Braginsky, Mathur
R package metabias
Common components — classes, methods, and documentation — for meta-analysis packages.
With Braginsky, Mathur
R package truncnormbayes
Bayesian estimation of the parameters of a truncated normal distribution.
With Braginsky, King, Mathur
R package phacking
Sensitivity analysis for p-hacking in meta-analyses.
With Braginsky, Mathur
R package regmedint
Regression-based causal mediation analysis.
With Yoshida, Li, Mathur
R package PublicationBias
Sensitivity analyses for publication bias in meta-analyses.
With Mathur, Wang, VanderWeele
R package MetaUtility
Estimate the proportion of effects stronger than a threshold of scientific importance, effect-size conversions, and meta-analytic inference helpers.
With Mathur, VanderWeele
R package NRejections
Metrics of outcome-wide evidence strength for studies testing multiple correlated outcomes.
With Mathur, VanderWeele
R package EValue
Sensitivity analyses for unmeasured confounding or selection bias in observational studies and meta-analyses.
With Mathur, Ding, Smith, VanderWeele
R package Replicate
Statistical analyses for multisite replication projects.
With Mathur, VanderWeele
R package SimTimeVar
Simulate a longitudinal dataset with time-varying covariates with user-specified correlation structures across and within clusters.
With Mathur, Kapphahn, Garcia, Desai, Montez-Rath

Stata module

1 module
Stata module EVALUE
Sensitivity analyses for unmeasured confounding in observational studies.
With Linden, VanderWeele, Mathur