hughesevoanth/glsmr: GAM and linear stratified observational and MR estimates of exposure on outcome

A pacakge to derive observational & causal estimates, in a Mendelian Randomization framework, for exposure on outcome relationships that may be non-linear. The package will fit both a linear and a generalized additive model (GAM) to the data, and will stratify your exposure to derive linear estimates for each strata. Non-linearity can be evaluated by testing the GAM to the linear model over the entire data or by evaluating heterogenity in the strata point estimates.

install.packages("remotes")
remotes::install_github("hughesevoanth/glsmr")