Edinburgh Research Explorer

Model Criticism in Latent Space

Research output: Contribution to journalArticle

Related Edinburgh Organisations

Open Access permissions

Open

Documents

  • Download as Adobe PDF

    Final published version, 1 MB, PDF-document

    Licence: Creative Commons: Attribution (CC-BY)

https://projecteuclid.org/euclid.ba/1560240024
Original languageEnglish
Pages (from-to)703-725
Number of pages23
JournalBayesian analysis
Volume14
Issue number3
Early online date26 Sep 2018
DOIs
Publication statusPublished - 11 Jun 2019

Abstract

Model criticism is usually carried out by assessing if replicated data generated under the fitted model looks similar to the observed data, see e.g. Gelman, Carlin, Stern, and Rubin (2004, p. 165). This paper presents a method for latent variable models by pulling back the data into the space of latent variables, and carrying out model criticism in that space. Making use of a model’s structure enables a more direct assessment of the assumptions made in the prior and likelihood. We demonstrate the method with examples of model criticism in latent space applied to factor analysis, linear dynamical systems and Gaussian processes.

Download statistics

No data available

ID: 75329362