From Stein Identities to Moderate Deviations
Preprint
Abstract
Stein's method is applied to obtain a Cram\'er type moderate deviation result for dependent random variables whose dependence is defined in terms of a Stein identity. A corollary for zero-bias coupling is deduced. The result is also applied to a combinatorial central limit theorem, a general system of binary codes, the anti-voter model on a complete graph, and the Curie-Weiss model. A general moderate deviation result for independent random variables is also proved.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Distribution of the sum-of-digits function of random integers: A surveyProbability Surveys, 2014
- Nonnormal approximation by Stein’s method of exchangeable pairs with application to the Curie–Weiss modelThe Annals of Applied Probability, 2011
- Applications of Stein’s method for concentration inequalitiesThe Annals of Probability, 2010
- A new method of normal approximationThe Annals of Probability, 2008
- Normal approximation under local dependenceThe Annals of Probability, 2004
- On coupling constructions and rates in the CLT for dependent summands with applications to the antivoter model and weighted $U$-statisticsThe Annals of Applied Probability, 1997
- Stein's method and the zero bias transformation with application to simple random samplingThe Annals of Applied Probability, 1997
- Stein's method for diffusion approximationsProbability Theory and Related Fields, 1990
- Limit theorems for sums of dependent random variables occurring in statistical mechanicsProbability Theory and Related Fields, 1978
- The Distribution of Leading Digits and Uniform Distribution Mod 1The Annals of Probability, 1977