Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Software Application Profile
T2 - Bayesian estimation of inverse variance weighted and MR-Egger models for two-sample Mendelian randomization studies-mrbayes
AU - Uche-Ikonne, O.
AU - Dondelinger, F.
AU - Palmer, T.
PY - 2021/2/28
Y1 - 2021/2/28
N2 - Motivation: We present our package, mrbayes, for the open source software environment R. The package implements Bayesian estimation for inverse variance weighted (IVW) and MR-Egger models, including the radial MR-Egger model, for summary-level data in Mendelian randomization (MR) analyses. Implementation: We have implemented a choice of prior distributions for the model parameters, namely; weakly informative, non-informative, a joint prior for the MR-Egger model slope and intercept, and an informative prior (pseudo-horseshoe prior), or the user can specify their own prior distribution. General features: Users have the option of fitting the models using either JAGS or Stan software packages with similar prior distributions; the option for the user-defined prior distribution is only in our JAGS functions. We show how to use the package through an applied example investigating the causal effect of body mass index (BMI) on acute ischaemic stroke. Availability: The package is freely available, under the GNU General Public License v3.0, on GitHub [https://github.com/okezie94/mrbayes] or CRAN [https://CRAN.R-project.org/package=mrbayes].
AB - Motivation: We present our package, mrbayes, for the open source software environment R. The package implements Bayesian estimation for inverse variance weighted (IVW) and MR-Egger models, including the radial MR-Egger model, for summary-level data in Mendelian randomization (MR) analyses. Implementation: We have implemented a choice of prior distributions for the model parameters, namely; weakly informative, non-informative, a joint prior for the MR-Egger model slope and intercept, and an informative prior (pseudo-horseshoe prior), or the user can specify their own prior distribution. General features: Users have the option of fitting the models using either JAGS or Stan software packages with similar prior distributions; the option for the user-defined prior distribution is only in our JAGS functions. We show how to use the package through an applied example investigating the causal effect of body mass index (BMI) on acute ischaemic stroke. Availability: The package is freely available, under the GNU General Public License v3.0, on GitHub [https://github.com/okezie94/mrbayes] or CRAN [https://CRAN.R-project.org/package=mrbayes].
KW - Inverse variance weighted
KW - JAGS
KW - Mendelian randomization
KW - MR-Egger model
KW - R
KW - Stan
U2 - 10.1093/ije/dyaa191
DO - 10.1093/ije/dyaa191
M3 - Journal article
VL - 50
SP - 43
EP - 49
JO - International Journal of Epidemiology
JF - International Journal of Epidemiology
SN - 0300-5771
IS - 1
ER -