gatk-3.8/java
ebanks b282635b05 Complete reworking of Fisher's exact test for strand bias:
- fixed math bug (pValue needs to be initialized to pCutoff, not 0)
- perform factorial calculations in log space so that huge numbers don't explode
- cache factorial calculations so that each value needs to be computed just once for any given instance of the filter

I've tested it against R and it has held up so far...



git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@1341 348d0f76-0448-11de-a6fe-93d51630548a
2009-07-30 18:52:13 +00:00
..
config Provide a default logger, some config settings, and some doc updates. 2009-04-29 02:06:05 +00:00
src/org/broadinstitute/sting Complete reworking of Fisher's exact test for strand bias: 2009-07-30 18:52:13 +00:00
test/org/broadinstitute/sting Adding the intial changes for the new Genotyping interface. The bullet points are: 2009-07-29 19:43:59 +00:00