Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 27, 2026The American Statistician

Collinear Groupwise Selection via Scaled Group Lasso

View Full Paper
Ask AI
Bookmark
Share

Authors

BYBahadır YüzbaşıJCJiguo Cao

Discussion

Loading...

Member takes

Overview

Randomized trial evaluates model selection effectiveness in regression with grouped covariates, indicating improved accuracy and sparsity.

Key Points

  • This work aims to develop a method for effective model selection and estimation in multiple linear regression with grouped variables.
  • Introduced Scaled Group Lasso (SGLASSO) to manage correlation among groups.
  • Implemented a block-wise coordinate descent algorithm with sequential screening.
  • Conducted simulations and real-data applications to assess performance.
  • SGLASSO improved prediction accuracy and coefficient estimation while maintaining model sparsity under collinearity.
  • Demonstrated enhanced computational efficiency with the proposed algorithm.
  • Supported by simulations showing effective parameter estimation in high-dimensional settings.

Cite This Study

Yüzbaşı et al. (2026) studied this question.

synapsesocial.com/papers/6a67007840bca442e0d4a2dahttps://doi.org/10.1080/00031305.2026.2709494
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Sparse Group Penalties for bi‐level variable selection2024 · 4 citations
  2. 2Interpretability of bi‐level variable selection methods2024 · 2 citations
  3. 3Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps2024
  4. 4Regression Shrinkage and Selection Via the Lasso1996 · 53,140 citations
  5. 5Bayesian group Lasso regression for left-censored data2020