Table of Contents Author Guidelines Submit a Manuscript
BioMed Research International
Volume 2016 (2016), Article ID 8209453, 11 pages
Research Article

High Dimensional Variable Selection with Error Control

Department of Biostatistics and Bioinformatics, Duke University Medical Center, Box 2717, Durham, NC 27710, USA

Received 3 April 2016; Accepted 25 May 2016

Academic Editor: Weiwei Zhai

Copyright © 2016 Sangjin Kim and Susan Halabi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Supplementary Material

Supplementary file is composed of the six parts of additional information that were not explained in the manuscript. Table S1 and S2 are the comparison of the performance for random filtering screening and FDR screenings with independent and moderate correlation ρ = {0, 0.4}, respectively in the simulation studies. Table S3 represents average true regression coefficients for the 25 variables through 500 replicates. Table S4 is comparison of area under the curve (AUC) and the corresponding 95% confidence interval with three popular variable selection methods (LASSO, SCAD, and MCP) for random screenings (1000,2000, and 4000) and FDR screenings at α = 0.01,0.05, and 0.20. Figure S1 and S2 shows the selection frequencies of each of the 25 variables across the LASSO, SCAD, and the MCP during 500 simulations with independent and moderate correlation ρ = {0, 0.4}. Figure S3 and S4 present AUC scores and the corresponding mean false discovery rate during the simulations with ρ = {0, 0.4}. Finally, Figure S5 shows boxplots of the expressions of 12 identified genes on metastasis in the prostate cancer.

  1. Supplementary Material