| pubmed-article:1316828 | pubmed:abstractText | A collection of sample size tables are presented for designing comparative trials when the event rates p1 and p2 are low. The tables are based on exact power calculations for Fisher's Exact Test. Both one-sided and two-sided alternative hypotheses are considered. A comparison is made between these sample sizes and those obtained by using popular asymptotic approximations. | lld:pubmed |
