The Annals of Probability

On Approximating Probabilities for Small and Large Deviations in $\mathbb{R}^d$

J. Robinson, T. Hoglund, L. Holst, and M. P. Quine

Full-text: Open access

Abstract

A unified approach to approximations of probabilities for sums of $n$ independent random vectors in $\mathbb{R}^d$ is presented based on the Edgeworth expansion of exponentially shifted vectors together with explicit bounds on the errors. Weak conditions are given under which the error bounds may be written as simple order terms in $n$. These results are used in particular to examine approximations to conditional probabilities giving a general method of approximation for these. A number of important special cases are discussed and examined numerically.

Article information

Source
Ann. Probab., Volume 18, Number 2 (1990), 727-753.

Dates
First available in Project Euclid: 19 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aop/1176990856

Digital Object Identifier
doi:10.1214/aop/1176990856

Mathematical Reviews number (MathSciNet)
MR1055431

Zentralblatt MATH identifier
0704.60018

JSTOR
links.jstor.org

Subjects
Primary: 60F05: Central limit and other weak theorems
Secondary: 60F10: Large deviations 62E20: Asymptotic distribution theory

Keywords
Edgeworth expansions saddlepoint approximations large deviations limit theorems conditional probabilities

Citation

Robinson, J.; Hoglund, T.; Holst, L.; Quine, M. P. On Approximating Probabilities for Small and Large Deviations in $\mathbb{R}^d$. Ann. Probab. 18 (1990), no. 2, 727--753. doi:10.1214/aop/1176990856. https://projecteuclid.org/euclid.aop/1176990856


Export citation