L1 regularisation allows for the selection of the predictors. To obtain a flexible model, we considered all the possible interactions between the exposure status and covariates . Moreover, we used b-splines for the quantitative variables of the vector . We used the glmnet function included in the glmnet package.
Do you have any questions about this protocol?
Post your question to gather feedback from the community. We will also invite the authors of this article to respond.