Statistics Papers
Title
Document Type
Journal Article
Date of this Version
2010
Publication Source
Institute of Mathematical Statistics Collections
Volume
6
Start Page
22
Last Page
31
DOI
10.1214/10-IMSCOLL602
Abstract
The information inequality has been shown to be an effective tool for providing lower bounds for the minimax risk. Bounds based on the chi-square distance can sometimes offer a considerable improvement especially when applied iteratively. This paper compares these two methods in four examples including the bounded normal mean problem as well as obervations from a Poisson distribution.
Keywords
minimax lower bound, information inequality, bounded normal mean, Chi-square distance
Recommended Citation
Low, M. G. (2010). Chi-Square Lower Bounds. Institute of Mathematical Statistics Collections, 6 22-31. http://dx.doi.org/10.1214/10-IMSCOLL602
Included in
Mathematics Commons, Other Physical Sciences and Mathematics Commons, Statistics and Probability Commons
Date Posted: 27 November 2017