Saddlepoint approximations

Gatto, Riccardo (2015). Saddlepoint approximations. In: StatsRef: Statistics Reference Online (pp. 1-7). Wiley 10.1002/9781118445112.stat01796.pub2

[img] Text
paper4.pdf - Accepted Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (239kB) | Request a copy

The saddlepoint method provides accurate approximations for the distributions of many test statistics, estimators and for important probabilities arising in various stochastic models. The saddlepoint approximation is a large deviations technique which is substantially more accurate than limiting normal or Edgeworth approximations, especially in presence of very small sample sizes or very small probabilities. The outstanding accuracy of the saddlepoint approximation can be explained by the fact that it has bounded relative error.

Item Type:

Book Section (Encyclopedia Article)

Division/Institute:

08 Faculty of Science > Department of Mathematics and Statistics > Institute of Mathematical Statistics and Actuarial Science

UniBE Contributor:

Gatto, Riccardo

Subjects:

500 Science > 510 Mathematics

Publisher:

Wiley

Language:

English

Submitter:

Lutz Dümbgen

Date Deposited:

07 Apr 2016 10:49

Last Modified:

26 Jun 2016 02:13

Publisher DOI:

10.1002/9781118445112.stat01796.pub2

BORIS DOI:

10.7892/boris.77827

URI:

https://boris.unibe.ch/id/eprint/77827

Actions (login required)

Edit item Edit item
Provide Feedback