Edinburgh Research Explorer

An Upper Bound on the Bayesian Error Bars for Generalized Linear Regression

Research output: Chapter in Book/Report/Conference proceedingChapter

Original languageEnglish
Title of host publicationMathematics of Neural Networks
Subtitle of host publicationModels, Algorithms and Applications
Place of PublicationNorwell, MA, USA
PublisherSpringer US
Pages295-299
Number of pages5
DOIs
Publication statusPublished - 1997

Publication series

NameOperations Research/Computer Science Interfaces Series
PublisherSpringer US
Volume8
ISSN (Print)1387-666X

Abstract

In the Bayesian framework, predictions for a regression problem are expressed in terms of a distribution of output values. The mode of this distribution corresponds to the most probable output, while the uncertainty associated with the predictions can conveniently be expressed in terms of error bars given by the standard deviation of the output distribution. In this paper we consider the evaluation of error bars in the context of the class of generalized linear regression models. We provide insights into the dependence of the error bars on the location of the data points and we derive an upper bound on the true error bars in terms of the contributions from individual data points which are themselves easily evaluated.

ID: 21977777