We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Sequential selection of variables using short permutation procedures and multiple adjustments: An application to genomic data.
- Authors
Azevedo Costa, Marcelo; de Souza Rodrigues, Thiago; da Costa, André Gabriel F. C.; Natowicz, René; Pádua Braga, Antônio; da Costa, André Gabriel Fc
- Abstract
This work proposes a sequential methodology for selecting variables in classification problems in which the number of predictors is much larger than the sample size. The methodology includes a Monte Carlo permutation procedure that conditionally tests the null hypothesis of no association among the outcomes and the available predictors. In order to improve computing aspects, we propose a new parametric distribution, the Truncated and Zero Inflated Gumbel Distribution. The final application is to find compact classification models with improved performance for genomic data. Results using real data sets show that the proposed methodology selects compact models with optimized classification performances.
- Subjects
MATHEMATICAL variables; GENOMICS; SEQUENTIAL analysis; STATISTICAL methods in genetics; CLASSIFICATION algorithms; ALGORITHMS; BREAST tumors; COMPUTER simulation; DATABASES; MULTIVARIATE analysis; SYSTEM analysis; SAMPLE size (Statistics); DATA analysis; GENE expression profiling; STATISTICAL models; STATISTICS
- Publication
Statistical Methods in Medical Research, 2017, Vol 26, Issue 2, p997
- ISSN
0962-2802
- Publication type
journal article
- DOI
10.1177/0962280214566262