We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
ON SOME TESTING OF HYPOTHESIS PROBLEMS WITH INFORMATION CONSTRAINTS.
- Authors
Burnashev, M. V.; Amari, Sh.; Han, T. S.
- Abstract
A problem of hypothesis testing is considered where some part of the data cannot be directly observed. Our helper observes those data and can send us some limited amount of information about them. What kind of information allows us to make the best statistical inferences? In particular, what is the minimal information sufficient in order to get the same results as if we could directly observe all the data? Some upper bounds for that minimal amount of information and some related results are obtained.
- Subjects
HYPOTHESIS; MAXIMA &; minima; STATISTICS; COGNITIVE interference
- Publication
Theory of Probability & Its Applications, 2001, Vol 45, Issue 4, p558
- ISSN
0040-585X
- Publication type
Article
- DOI
10.1137/S0040585X97978506