Structured variable selection with q-values

Tanya P. Garcia*, Samuel Müller, Raymond J. Carroll, Tamara N. Dunn, Anthony P. Thomas, Sean H. Adams, Suresh D. Pillai, Rosemary L. Walzem

*Corresponding author for this work

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

When some of the regressors can act on both the response and other explanatory variables, the already challenging problem of selecting variables when the number of covariates exceeds the sample size becomes more difficult. A motivating example is a metabolic study in mice that has diet groups and gut microbial percentages that may affect changes in multiple phenotypes related to body weight regulation. The data have more variables than observations and diet is known to act directly on the phenotypes as well as on some or potentially all of the microbial percentages. Interest lies in determining which gut microflora influence the phenotypes while accounting for the direct relationship between diet and the other variables. A new methodology for variable selection in this context is presented that links the concept of q-values from multiple hypothesis testing to the recently developed weighted Lasso.

Original languageEnglish
Pages (from-to)695-707
Number of pages13
JournalBiostatistics
Volume14
Issue number4
DOIs
Publication statusPublished - Sep 2013
Externally publishedYes

Keywords

  • False discovery rate
  • Microbial data
  • q-Values
  • Variable selection
  • Weighted Lasso

Fingerprint Dive into the research topics of 'Structured variable selection with q-values'. Together they form a unique fingerprint.

Cite this