Abstract
Motivation In recent years Mendelian randomization analysis using summary data from genome-wide association studies has become a popular approach for investigating causal relationships in epidemiology. The mrrobust Stata package implements several of the recently developed methods.
Implementation mrrobust is freely available as a Stata package.
General Features The package includes inverse variance weighted estimation, as well as a range of median and MR-Egger estimation methods. Using mrrobust, plots can be constructed visualising each estimate either individually or simultaneously. The package also provides statistics such as , which are useful in assessing attenuation bias in causal estimates.
Availability The software is freely available from GitHub [https://raw.github.com/remlapmot/mrrobust/master/].