From 482b0ec7dc0aa7cb3a49b8ce304fdb1ae41e679c Mon Sep 17 00:00:00 2001 From: Alex Zwanenburg Date: Wed, 4 Dec 2024 17:23:17 +0100 Subject: [PATCH] Fixed wrong argument name. --- vignettes/original/evaluation_and_explanation.Rmd | 2 +- vignettes/original/introduction.Rmd | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/vignettes/original/evaluation_and_explanation.Rmd b/vignettes/original/evaluation_and_explanation.Rmd index 824bb25f..f7b10f49 100644 --- a/vignettes/original/evaluation_and_explanation.Rmd +++ b/vignettes/original/evaluation_and_explanation.Rmd @@ -84,7 +84,7 @@ plots, do not benefit from bootstraps as they are solely based on values predicted by the (ensemble) models. If you want to compute bias-corrected estimates or bootstrap confidence intervals for these analyses you should ensure that sufficient models are created. Experimental designs such as -`experiment_design="bs(fs+mb,400)+ev"` allow for this, but are computationally +`experimental_design="bs(fs+mb,400)+ev"` allow for this, but are computationally expensive. | Name | Plot function | Export function | Estimation type | Detail level | Sample limit | Stand-alone | diff --git a/vignettes/original/introduction.Rmd b/vignettes/original/introduction.Rmd index 05a905e4..1984072d 100644 --- a/vignettes/original/introduction.Rmd +++ b/vignettes/original/introduction.Rmd @@ -494,14 +494,14 @@ Familiar implements the following subsampling methods: The `x` argument of subsample methods can contain one or more of the workflow components. Moreover, it is possible to nest subsample methods. For example, -`experiment_design="cv(bt(fs,50)+mb,5)+ev"` would create a 5-fold +`experimental_design="cv(bt(fs,50)+mb,5)+ev"` would create a 5-fold cross-validation of the development dataset, with each set of training folds again subsampled for computing variable importances. After aggregating variable importance obtained over 50 bootstraps, a model is trained within each set of training folds, resulting in 5 models overall. The ensemble of these models is then evaluated on an external dataset. -Other designs, such as `experiment_design="bs(fs+mb,400)+ev"` allow for building +Other designs, such as `experimental_design="bs(fs+mb,400)+ev"` allow for building large ensembles, and capturing the posterior distribution of the model predictions.