Answers are grounded in this paper and cite their sources.
Closed sequential tests of two types are considered. I: Repeated significance tests on accumulating data: II: as above, except that at each stage the critical value is taken to be the value corresponding to all n observations. These are applied to testing the parameter of a uniform distribution. In this case there exists a uniformly best test, different from both the above tests.
No takes yet. Share an insight, caveat, or question.
Ester Samuel‐Cahn (1974) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: