4.7 Article

Sparse partial least-squares regression and its applications to high-throughput data analysis

期刊

出版社

ELSEVIER
DOI: 10.1016/j.chemolab.2011.07.002

关键词

Lasso; Modeling; Prediction; Regression analyses; Variable selection

资金

  1. Swedish Research Council
  2. National Research Foundation of Korea(NRF)
  3. Ministry of Education, Science and Technology [2010-0011372]
  4. National Research Foundation of Korea [2010-0011372] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)

向作者/读者索取更多资源

The partial least-squares (PLS) method is designed for prediction problems where the number of predictors is larger than the number of training samples. PIS is based on latent components that are linear combinations of all of the original predictors, so it automatically employs all predictors regardless of their relevance. This will potentially compromise its performance, but it will also make it difficult to interpret the result. In this paper, we propose a new formulation of the sparse PIS (SPLS) procedure to allow both sparse variable selection and dimension reduction. We use the standard L-1-penalty and the unbounded penalty of [1]. We develop a computing algorithm for SPLS by modifying the nonlinear iterative partial least-squares (NIPALS) algorithm, and illustrate the method with an analysis of a cancer dataset. Through the numerical studies we find that our SPLS method generally performs better than the standard PIS and other existing methods in variable selection and prediction. (C) 2011 Elsevier B.V. All rights reserved.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据