A comparison of the discrimination performance of lasso and maximum likelihood estimation in logistic regression model

TL;DR

This study compares the discrimination performance of lasso and maximum likelihood estimation in logistic regression through simulation and real data, especially focusing on high covariate-to-sample size ratios.

Contribution

It provides a comprehensive comparison including simulation studies and applications, highlighting lasso's superior performance in high-dimensional scenarios.

Findings

Lasso outperforms MLE in discrimination when covariate-to-sample ratio is high.

Simulation results confirm the robustness of lasso in high-dimensional settings.

Variable selection methods influence the discrimination performance.

Abstract

Logistic regression is widely used in many areas of knowledge. Several works compare the performance of lasso and maximum likelihood estimation in logistic regression. However, part of these works do not perform simulation studies and the remaining ones do not consider scenarios in which the ratio of the number of covariates to sample size is high. In this work, we compare the discrimination performance of lasso and maximum likelihood estimation in logistic regression using simulation studies and applications. Variable selection is done both by lasso and by stepwise when maximum likelihood estimation is used. We consider a wide range of values for the ratio of the number of covariates to sample size. The main conclusion of the work is that lasso has a better discrimination performance than maximum likelihood estimation when the ratio of the number of covariates to sample size is high.