One-sample Mendelian randomization (MR) / instrumental variable (IV) analyses in Stata.
- July 2024:
- Amend legend position in
ivmw
andivxtile
to use the 6 o'clock position as per in Stata 17 and earlier
- Amend legend position in
- January 2024:
- Reran certification scripts under Stata 18.0
- August 2023:
- Added a record of the Stata version in the certification scripts
- April 2023:
- The images in the package website now have accompanying alt text descriptions
- Checked the certification scripts run under the latest Stata 17.0
- Rewrote the website using Quarto
- February 2023:
- Updated the R Markdown code generating the website to use the CRAN version of the Statamarkdown package
- November 2022:
- For an example Mendelian randomization analysis using ivonesamplemr please see Madley-Dowd et al., Maternal vitamin D during pregnancy and offspring autism and autism-associated traits: a prospective cohort study, Molecular Autism, 2022, here
- February 2022:
- Ran cscripts under Stata 17.0
- ivonesamplemr now has a website https://remlapmot.github.io/ivonesamplemr/
The package includes implementations of:
- additive structural mean model: see
help ivasmm
- logistic structural mean model: see
help ivlsmm
- multiplicative structural mean model: see
help ivmsmm
- two-stage predictor substitution estimators: see
ivtsps
- two-stage residual inclusion estimators: see
help ivtsri
- moving window (a.k.a. sliding/rolling window) versions of these estimators: see
help ivmw
- performing estimation within quantiles of the first stage residuals: see
help ivxtile
The ivtsps
and ivtsri
commands implement the following link functions for the second stage model:
- identity (i.e. linear regression) - for a binary outcome this estimates a causal risk difference
- logadd (log additive, i.e. Poisson/log-binomial regression) and logmult (log multiplicative, i.e. gamma regression) - for a binary outcome these estimate a causal risk ratio
- logit (i.e. logistic regression) - for a binary outcome this estimates a causal odds ratio
Install the ivonesamplemr package within Stata using
net install github, from("https://haghish.github.io/github/")
github install remlapmot/ivonesamplemr
Or use the following code
net install ivonesamplemr, from("https://raw.github.com/remlapmot/ivonesamplemr/main/") replace
do "https://raw.github.com/remlapmot/ivonesamplemr/main/dependency.do"
Launch the main package helpfile with
help ivonesamplemr
To check for an update to the package run within Stata
adoupdate ivonesamplemr, update
Uninstall the package within Stata using
ado uninstall ivonesamplemr