False discovery rate, sensitivity and sample size for microarray studies Export

@article{citeulike:233327, abstract = {Motivation: In microarray data studies most researchers are keenly aware of the potentially high rate of false positives and the need to control it. One key statistical shift is the move away from the well-known P-value to false discovery rate (FDR). Less discussion perhaps has been spent on the sensitivity or the associated false negative rate (FNR). The purpose of this paper is to explain in simple ways why the shift from P-value to FDR for statistical assessment of microarray data is necessary, to elucidate the determining factors of FDR and, for a two-sample comparative study, to discuss its control via sample size at the design stage. Results: We use a mixture model, involving differentially expressed (DE) and non-DE genes, that captures the most common problem of finding DE genes. Factors determining FDR are (1) the proportion of truly differentially expressed genes, (2) the distribution of the true differences, (3) measurement variability and (4) sample size. Many current small microarray studies are plagued with large FDR, but controlling FDR alone can lead to unacceptably large FNR. In evaluating a design of a microarray study, sensitivity or FNR curves should be computed routinely together with FDR curves. Under certain assumptions, the FDR and FNR curves coincide, thus simplifying the choice of sample size for controlling the FDR and FNR jointly. Availability: R-package OCplus for computing FDR, sensitivity curves and sample size is freely available at http://www.meb.ki.se/\~{}yudpaw Contact: yudi.pawitan@meb.ki.se 10.1093/bioinformatics/bti448}, author = {Pawitan, Yudi and Michiels, Stefan and Koscielny, Serge and Gusnanto, Arief and Ploner, Alexander}, citeulike-article-id = {233327}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/bti448}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/bti448v2/.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/bti448v2/.full.pdf}, citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/21/13/3017}, citeulike-linkout-4 = {http://www.ingentaconnect.com/content/oup/cabios/2005/00000021/00000013/art03017}, citeulike-linkout-5 = {http://view.ncbi.nlm.nih.gov/pubmed/15840707}, citeulike-linkout-6 = {http://www.hubmed.org/display.cgi?uids=15840707}, day = {1}, doi = {10.1093/bioinformatics/bti448}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {discovery, false, fdr, microarray, rate}, month = {July}, number = {13}, pages = {3017--3024}, posted-at = {2008-03-12 10:27:07}, priority = {2}, publisher = {Oxford University Press}, title = {False discovery rate, sensitivity and sample size for microarray studies}, url = {http://dx.doi.org/10.1093/bioinformatics/bti448}, volume = {21}, year = {2005} }

TY - JOUR ID - citeulike:233327 L3 - citeulike-article-id:233327 N2 - Motivation: In microarray data studies most researchers are keenly aware of the potentially high rate of false positives and the need to control it. One key statistical shift is the move away from the well-known P-value to false discovery rate (FDR). Less discussion perhaps has been spent on the sensitivity or the associated false negative rate (FNR). The purpose of this paper is to explain in simple ways why the shift from P-value to FDR for statistical assessment of microarray data is necessary, to elucidate the determining factors of FDR and, for a two-sample comparative study, to discuss its control via sample size at the design stage. Results: We use a mixture model, involving differentially expressed (DE) and non-DE genes, that captures the most common problem of finding DE genes. Factors determining FDR are (1) the proportion of truly differentially expressed genes, (2) the distribution of the true differences, (3) measurement variability and (4) sample size. Many current small microarray studies are plagued with large FDR, but controlling FDR alone can lead to unacceptably large FNR. In evaluating a design of a microarray study, sensitivity or FNR curves should be computed routinely together with FDR curves. Under certain assumptions, the FDR and FNR curves coincide, thus simplifying the choice of sample size for controlling the FDR and FNR jointly. Availability: R-package OCplus for computing FDR, sensitivity curves and sample size is freely available at http://www.meb.ki.se/~yudpaw Contact: yudi.pawitan@meb.ki.se 10.1093/bioinformatics/bti448 IS - 13 JF - Bioinformatics SN - 1367-4803 EP - 3024 TI - False discovery rate, sensitivity and sample size for microarray studies PB - Oxford University Press VL - 21 SP - 3017 KW - discovery KW - false KW - fdr KW - microarray KW - rate AU - Pawitan, Yudi AU - Michiels, Stefan AU - Koscielny, Serge AU - Gusnanto, Arief AU - Ploner, Alexander PY - 2005/07/01/ UR - http://dx.doi.org/10.1093/bioinformatics/bti448 ER -