Transformations in semi-parametric Bayesian synthetic likelihood

Jacob W. Priddle and Christopher Drovandi

Computational Statistics & Data Analysis, 2023, vol. 187, issue C

Abstract: Bayesian synthetic likelihood (BSL) is an established method for performing approximate Bayesian inference when the likelihood function is intractable. In synthetic likelihood methods, the likelihood function is approximated parametrically via model simulations, and then standard likelihood-based techniques are used to perform inference. The Gaussian synthetic likelihood estimator has become ubiquitous in BSL literature, primarily for its simplicity and ease of implementation. However, it is often too restrictive and may lead to poor posterior approximations. Recently, a more flexible semi-parametric Bayesian synthetic likelihood (semiBSL) estimator has been introduced, which is significantly more robust to irregularly distributed summary statistics. A number of extensions to semiBSL are proposed. First, even more flexible estimators of the marginal distributions are considered, using transformation kernel density estimation. Second, whitening semiBSL (wsemiBSL) is proposed – a method to significantly improve the computational efficiency of semiBSL. wsemiBSL uses an approximate whitening transformation to decorrelate summary statistics at each algorithm iteration. The methods developed herein significantly improve the versatility and efficiency of BSL algorithms.

Keywords: Likelihood-free inference; Approximate Bayesian computation (ABC); Kernel density estimation; Copula; Covariance matrix estimation; Markov chain Monte Carlo (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167947323001081
Full text for ScienceDirect subscribers only.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:csdana:v:187:y:2023:i:c:s0167947323001081

DOI: 10.1016/j.csda.2023.107797

Access Statistics for this article

Computational Statistics & Data Analysis is currently edited by S.P. Azen

More articles in Computational Statistics & Data Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().