Comparing the accuracy and parsimony of LASSO and backward selection prediction models across varying sample sizes

Communications in Statistics Case Studies Data Analysis and Applications 2026 Open access

Read full text
Authors: Sun Young Jeon, Sei J. Lee, Bocheng Jing, Alexandra K. Lee, William James Deardorff, W. John Boscardin
DOI: 10.1080/23737484.2026.2622374
Cited by: 0
References: 20

Abstract

LASSO and backward selection methods were used to develop prediction models in electronic health record (EHR) data, varying the sample size (n) while holding the number of predictors (p) fixed. Utilizing Veterans Affairs (VA) EHR data from 2005 with vital status follow-up until 2017, we employed four modeling strategies across six sample sizes: LASSO with cross-validated λ and Bayesian information criterion (BIC) λ, backward selection using BIC, and p

Fields of Study & Subjects

Statistical Methods and Inference Statistical Methods in Epidemiology Machine Learning in Healthcare

Publication details

Journal / source
Communications in Statistics Case Studies Data Analysis and Applications
Volume
12
Issue
2
Pages
157–168
Publication date
28 February 2026
Language
EN