Is there a simple example for a pair of hypotheses for which a uniformly most powerful (UMP) test does not exist? How does one go about proving this? Is it true that for tests with double-sided hypotheses, a UMP test does not exist? Is it true that for multivariate parameters, a UMP tests does not exist?
$\begingroup$
$\endgroup$
2
-
$\begingroup$ split this into multiple questions $\endgroup$– Chill2MachtCommented Oct 16, 2017 at 15:37
-
$\begingroup$ stats.stackexchange.com/q/188752/119261, stats.stackexchange.com/q/181255/119261 $\endgroup$– StubbornAtomCommented Jul 22, 2020 at 19:56
Add a comment
|