Testing Against Independence and a Rényi Information Measure
Preprint
Abstract
The achievable error-exponent pairs for the type I and type II errors are characterized in a hypothesis testing setup where the observation consists of independent and identically distributed samples from either a known joint probability distribution or an unknown product distribution. The empirical mutual information test, the Hoeffding test, and the generalized likelihood-ratio test are all shown to be asymptotically optimal. An expression based on a Renyi measure of dependence is shown to be the Fenchel biconjugate of the error-exponent function obtained by fixing one error exponent and optimizing the other. An example is provided where the error-exponent function is not convex and thus not equal to its Fenchel biconjugate.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Operational Interpretation of Rényi Information Measures via Composite Hypothesis Testing Against Product and Markov DistributionsIEEE Transactions on Information Theory, 2017
- Motivations for an Arbitrary Precision Interval Arithmetic and the MPFI LibraryReliable Computing, 2005
- Universal composite hypothesis testing: a competitive minimax approachIEEE Transactions on Information Theory, 2002
- When is the generalized likelihood ratio test optimal?IEEE Transactions on Information Theory, 1992
- Hypothesis testing and information theoryIEEE Transactions on Information Theory, 1974
- Asymptotically Optimal Tests for Multinomial DistributionsThe Annals of Mathematical Statistics, 1965