12,000

We have over 12,000 students, from over 100 countries, within one of the safest campuses in the UK

93%

93% of Lancaster students go into work or further study within six months of graduating

Home > Research > Publications & Outputs > A comparative review of dimension reduction met...
View graph of relations

« Back

A comparative review of dimension reduction methods in approximate Bayesian computation

Research output: Contribution to journalJournal article

Published

Journal publication date05/2013
JournalStatistical Science
Journal number2
Volume28
Number of pages20
Pages189-208
Early online date1/11/12
Original languageEnglish

Abstract

Approximate Bayesian computation (ABC) methods make use of comparisons between simulated and observed summary statistics to overcome the problem of computationally intractable likelihood functions. As the practical implementation of ABC requires computations based on vectors of summary statistics, rather than full datasets, a central question is how to derive low dimensional summary statistics from the observed data with minimal loss of information. In this article we provide a comprehensive review and comparison of the performance of the principal methods of dimension reduction proposed in the ABC literature. The methods are split into three non-mutually exclusive classes consisting of best subset selection methods, projection techniques and regularisation. In addition, we introduce two new methods of dimension reduction. The first is a best subset selection method based on Akaike and Bayesian information criteria, and the second uses ridge regression as a regularisation procedure. We illustrate the performance of these dimension reduction techniques through the analysis of three challenging models and data sets.