Both the Fisher exact test and sage.test (in sagenhaft) can produce p-values slightly bigger than 1. This can mess up down-stream analyses (like using qvalue, e.g.). Perhaps the functions could be modified to truncate the p-values at 1.0. Thanks, Naomi S. Altman 814-865-3791 (voice) Associate Professor Dept. of Statistics 814-863-7114 (fax) Penn State University 814-865-1348 (Statistics) University Park, PA 16802-2111