|
Organizers |
Multiple testing in large-scale gene expression experiments
by
Terry Speed
Walter & Eliza Hall Institute of Medical Research
Large-scale gene expression experiments using techniques such as SAGE or oligonucleotide or cDNA microarrays typically involve tens of thousands of genes. Such experiments are frequently comparative, so that we make tens of thousands of comparisons, seeking the “significant” ones. Under such circumstances care needs to be taken to adjust appropriately for the number of tests taken. Not surprisingly, Bonferroni is usually too severe, but the tests are correlated so that no simple alternative exists. In this talk I will outline some of the approaches which have been taken to this issue and mention some outstanding problems.
Date received: August 29, 2001
Copyright © 2001 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cahg-40.