On Testing and Estimating the Interaction Between Treatments and Environmental Conditions in Binomial Experiments, I: The Case of Two Stations.
STANFORD UNIV CALIF DEPT OF STATISTICS
Pagination or Media Count:
Estimating confidence intervals for the interaction between treatments and environmental conditions in binomial experiments is analyzed. Testing the interaction is studied also. The problem is reduced to that of estimating or testing the interaction parameter in 2x2x2 contingency tables with given marginals. Programs for determining the exact conditional tests and their power functions are provided for samples of size not exceeding 100. Large sample approximations based on maximum likelihood ML and on the arcsin transformation for proportions are studied. It is shown that the arcsin transformation is effective also in small samples and may yield asymmetric confidence intervals which are shorter than exact conditional confidence limits.
- Statistics and Probability