Please use this identifier to cite or link to this item:
Title: Searching for differential expression: a non-parametric approach
Author: Ortega-Serrano, I.
Ruiz de Villa, Carmen
Miñarro Alonso, Antonio
Keywords: Distribució (Teoria de la probabilitat)
Mètodes estadístics
Microxips d'ADN
Distribution (Probability theory)
Statistical methods
DNA microarrays
Issue Date: 2012
Publisher: Taylor and Francis
Abstract: Microarray experiments are being widely used in medical and biological research. The main features of these studies are the large number of variables (genes) involved and the low number of replicates (arrays). It seems clear that the most appropriate models, when looking for detecting differences in gene expression are those that exploit the most useful information to compensate for the lack of replicates. On the other hand, the control of the error in the decision process plays an important role for the high number of simultaneous statistical tests (one for each gene), so that concepts such as the false discovery rate (FDR) take a special importance. One of the alternatives for the analysis of the data in these experiments is based on the calculation of statistics derived from modifications of the classical methods used in this type of problems (moderated-t, B-statistic). Nonparametric techniques have been also proposed [B. Efron, R. Tibshirani, J.D. Storey, andV. Tusher, Empirical Bayes analysis of a microarray experiment, J. Amer. Stat. Assoc. 96 (2001), pp. 1151 1160; W. Pan, J. Lin, and C.T. Le, A mixture model approach to detecting differentially expressed genes with microarray data, Funct. Integr. Genomics 3 (2003), pp. 117 124], allowing the analysis without assuming any prior condition about the distribution of the data, which make them especially suitable in such situations. This paper presents a new method to detect differentially expressed genes based on non-parametric density estimation by a class of functions that allow us to define a distance between individuals in the sample (characterized by the coordinates of the individual (gene) in the dual space tangent to the manifold of parameters) [A. Miñarro and J.M. Oller, Some remarks on the individuals-score distance and its applications to statistical inference, Qüestiió, 16 (1992), pp. 43 57]. From these distances, we designed the test to determine the rejection region based on the control of FDR.
Note: Versió postprint del document publicat a:
It is part of: Journal of Statistical Computation and Simulation, 2012, vol. 83, num. 9, p. 1661-1670
Related resource:
ISSN: 0094-9655
Appears in Collections:Articles publicats en revistes (Genètica, Microbiologia i Estadística)

Files in This Item:
File Description SizeFormat 
609404.pdf226 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.