Statistical significance for genomewide studies.

@article{citeulike:241030, abstract = {With the increase in genomewide experiments and the sequencing of multiple genomes, the analysis of large data sets has become commonplace in biology. It is often the case that thousands of features in a genomewide data set are tested against some null hypothesis, where a number of features are expected to be significant. Here we propose an approach to measuring statistical significance in these genomewide studies based on the concept of the false discovery rate. This approach offers a sensible balance between the number of true and false positives that is automatically calibrated and easily interpreted. In doing so, a measure of statistical significance called the q value is associated with each tested feature. The q value is similar to the well known p value, except it is a measure of significance in terms of the false discovery rate rather than the false positive rate. Our approach avoids a flood of false positive results, while offering a more liberal criterion than what has been used in genome scans for linkage.}, address = {Department of Biostatistics, University of Washington, Seattle, WA 98195, USA. jstorey@u.washington.edu}, author = {Storey, J. D. and Tibshirani, R. }, citeulike-article-id = {241030}, doi = {10.1073/pnas.1530509100}, issn = {0027-8424}, journal = {Proc Natl Acad Sci U S A}, keywords = {gwa}, month = {August}, number = {16}, pages = {9440--9445}, posted-at = {2007-06-23 04:52:49}, priority = {2}, title = {Statistical significance for genomewide studies.}, url = {http://dx.doi.org/10.1073/pnas.1530509100}, volume = {100}, year = {2003} }

TY - JOUR ID - citeulike:241030 L3 - citeulike-article-id:241030 TI - Statistical significance for genomewide studies. JF - Proc Natl Acad Sci U S A VL - 100 IS - 16 SP - 9440 EP - 9445 AD - Department of Biostatistics, University of Washington, Seattle, WA 98195, USA. jstorey@u.washington.edu SN - 0027-8424 N2 - With the increase in genomewide experiments and the sequencing of multiple genomes, the analysis of large data sets has become commonplace in biology. It is often the case that thousands of features in a genomewide data set are tested against some null hypothesis, where a number of features are expected to be significant. Here we propose an approach to measuring statistical significance in these genomewide studies based on the concept of the false discovery rate. This approach offers a sensible balance between the number of true and false positives that is automatically calibrated and easily interpreted. In doing so, a measure of statistical significance called the q value is associated with each tested feature. The q value is similar to the well known p value, except it is a measure of significance in terms of the false discovery rate rather than the false positive rate. Our approach avoids a flood of false positive results, while offering a more liberal criterion than what has been used in genome scans for linkage. KW - gwa AU - Storey, JD AU - Tibshirani, R PY - 2003/08/05/ UR - http://dx.doi.org/10.1073/pnas.1530509100 ER -