KIT | KIT-Bibliothek | Impressum | Datenschutz

Predictive Inference Based on Markov Chain Monte Carlo Output

Krüger, Fabian; Lerch, Sebastian; Thorarinsdottir, Thordis; Gneiting, Tilmann

Abstract:
In Bayesian inference, predictive distributions are typically in the form of samples generated via Markov chain Monte Carlo or related algorithms. In this paper, we conduct a systematic analysis of how to make and evaluate probabilistic forecasts from such simulation output. Based on proper scoring rules, we develop a notion of consistency that allows to assess the adequacy of methods for estimating the stationary distribution underlying the simulation output. We then provide asymptotic results that account for the salient features of Bayesian posterior simulators and derive conditions under which choices from the literature satisfy our notion of consistency. Importantly, these conditions depend on the scoring rule being used, such that the choices of approximation method and scoring rule are intertwined. While the logarithmic rule requires fairly stringent conditions, the continuous ranked probability score yields consistent approximations under minimal assumptions. These results are illustrated in a simulation study and an economic data example. Overall, mixture‐of‐parameters approximations that exploit the parametric structure of Bayesian models perform particularly well. ... mehr

Open Access Logo


Verlagsausgabe §
DOI: 10.5445/IR/1000125350
Veröffentlicht am 28.10.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Stochastik (STOCH)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2020
Sprache Englisch
Identifikator ISSN: 0306-7734, 1751-5823
KITopen-ID: 1000125350
Erschienen in International statistical review
Vorab online veröffentlicht am 28.09.2020
Nachgewiesen in Scopus
Web of Science
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page