TESTS AND CONFIDENCE-INTERVALS FOR DIFFERENCE AND RATIO OF 2 PROBABILITIES
成果类型：
Note
署名作者：
BUHRMAN, JM
刊物名称：
BIOMETRIKA
ISSN/ISSBN：
0006-3444
DOI：
10.2307/2335791
发表日期：
1977
页码：
160162
关键词：
摘要：
Fisher''s (1925) test can deal with the hypothesis of equal probabilities of success of 2 experiments, A and B. The test requires a fixed number of experiments of both kinds. If the experimental design is changed into randomizing the numbers of experiments A and B, other kinds of hypotheses can be tested exactly and exact confidence intervals can be constructed.