MVMR directly from the GitHub repository, first make sure you have the
devtools package installed:
MVMR package can be installed using:
To update the package just run the
install_github("WSpiller/MVMR") command again.
We have written the
MVMR R package to perform multivariable Mendelian randomization analyses, including heterogeneity
statistics for assessing instrument strength and validity. The package accommodates any number of exposures greater than 1,
and is currently comprised of two functions:
format_mvmr function is used to convert a data frame containing summary data into a set format for MVMR analyses.
mvmr function fits an IVW multivariable Mendelian randomization model using first order weights. The function returns
an object of class
MVMRIVW, containing regression estimates, estimated heterogeneity as a measure of instrument strength
Q_strength), and estimated heterogeneity as a measure of instrument validity (
Q_valid). Estimation follows the method
outlined in Sanderson et al, 2018.
Multivariable Mendelian randomization is implemented in a number of R packages such as
however, this package includes further sensitivity analyses leveraging information on causal effect heterogeneity across instruments.
To incorporate these features and future developments we will continue to develop our own
MVMR package to implement multivariable
The corresponding paper has been published by the International Journal of Epidemiology, and can be accessed at:
This project is licensed under GNU GPL v3.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.