Riley, R, Snell, K, Martin, G, Whittle, R, Archer, L, Sperrin, M and Collins, G (2020) Penalisation and shrinkage methods can produce unreliable clinical prediction models especially when sample size is small. Journal of Clinical Epidemiology, 132. pp. 88-96. ISSN 1878-5921

[thumbnail of Shrinkage uncertainty - revised SUBMITTED.docx] Text
Shrinkage uncertainty - revised SUBMITTED.docx - Accepted Version

Download (7MB)


When developing a clinical prediction model, penalization techniques are recommended to address overfitting, as they shrink predictor effect estimates toward the null and reduce mean-square prediction error in new individuals. However, shrinkage and penalty terms (‘tuning parameters’) are estimated with uncertainty from the development data set. We examined the magnitude of this uncertainty and the subsequent impact on prediction model performance.

Study Design and Setting
This study comprises applied examples and a simulation study of the following methods: uniform shrinkage (estimated via a closed-form solution or bootstrapping), ridge regression, the lasso, and elastic net.

In a particular model development data set, penalization methods can be unreliable because tuning parameters are estimated with large uncertainty. This is of most concern when development data sets have a small effective sample size and the model's Cox-Snell is low. The problem can lead to considerable miscalibration of model predictions in new individuals.

Penalization methods are not a ‘carte blanche’; they do not guarantee a reliable prediction model is developed. They are more unreliable when needed most (i.e., when overfitting may be large). We recommend they are best applied with large effective sample sizes, as identified from recent sample size calculations that aim to minimize the potential for model overfitting and precisely estimate key parameters.

Item Type: Article
Uncontrolled Keywords: Risk prediction models, Penalization, Shrinkage, Overfitting, Sample size
Subjects: R Medicine > RA Public aspects of medicine
Divisions: Faculty of Medicine and Health Sciences > School of Medicine
Related URLs:
Depositing User: Symplectic
Date Deposited: 10 Dec 2020 16:54
Last Modified: 11 Jun 2021 11:30

Actions (login required)

View Item
View Item