Enrichment or depletion of a GO category within a class of genes: which test?

@article{citeulike:1056288, abstract = {MOTIVATION: A number of available program packages determine the significant enrichments and/or depletions of GO categories among a class of genes of interest. Whereas a correct formulation of the problem leads to a single exact null distribution, these GO tools use a large variety of statistical tests whose denominations often do not clarify the underlying p-value computations. SUMMARY: We review the different formulations of the problem and the tests they lead to: the binomial, chi-square, equality of two probabilities, Fisher's exact, and hypergeometric tests. We clarify the relationships existing between these tests, in particular the equivalence between the hypergeometric test and Fisher's exact test. We recall that the other tests are valid only for large samples, the test of equality of two probabilities and the chi-square test being equivalent. We discuss the appropriateness of one- and two-sided p-values, as well as some discreteness and conservatism issues.}, address = {\'{E}quipe de Statistique Appliqu\'{e}e, \'{E}cole Sup\'{e}rieure de Physique et de Chimie Industrielles (ESPCI), 10 rue Vauquelin, 75005 Paris, France.}, author = {Rivals, Isabelle and Personnaz, L\'{e}on and Taing, Lieng and Potier, Marie-Claude C. }, citeulike-article-id = {1056288}, doi = {10.1093/bioinformatics/btl633}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {bioinformatics, ease, mev, nested-ease}, month = {December}, posted-at = {2008-01-31 19:59:58}, priority = {2}, title = {Enrichment or depletion of a GO category within a class of genes: which test?}, url = {http://dx.doi.org/10.1093/bioinformatics/btl633}, year = {2006} }

TY - JOUR ID - citeulike:1056288 L3 - citeulike-article-id:1056288 TI - Enrichment or depletion of a GO category within a class of genes: which test? JF - Bioinformatics AD - Équipe de Statistique Appliquée, École Supérieure de Physique et de Chimie Industrielles (ESPCI), 10 rue Vauquelin, 75005 Paris, France. SN - 1460-2059 N2 - MOTIVATION: A number of available program packages determine the significant enrichments and/or depletions of GO categories among a class of genes of interest. Whereas a correct formulation of the problem leads to a single exact null distribution, these GO tools use a large variety of statistical tests whose denominations often do not clarify the underlying p-value computations. SUMMARY: We review the different formulations of the problem and the tests they lead to: the binomial, chi-square, equality of two probabilities, Fisher's exact, and hypergeometric tests. We clarify the relationships existing between these tests, in particular the equivalence between the hypergeometric test and Fisher's exact test. We recall that the other tests are valid only for large samples, the test of equality of two probabilities and the chi-square test being equivalent. We discuss the appropriateness of one- and two-sided p-values, as well as some discreteness and conservatism issues. KW - bioinformatics KW - ease KW - mev KW - nested-ease AU - Rivals, Isabelle AU - Personnaz, Léon AU - Taing, Lieng AU - Potier, Marie-Claude PY - 2006/12/20/ UR - http://dx.doi.org/10.1093/bioinformatics/btl633 ER -