Ullrika Sahlin
Universitetslektor
Hybrid elicitation and quantile-parametrized likelihood
Författare
Summary, in English
This paper extends the application of quantile-based Bayesian inference to probability distributions defined in terms of quantiles of observable quantities. Quantile-parameterized distributions are characterized by high shape flexibility and parameter interpretability, making them useful for eliciting information about observables. To encode uncertainty in the quantiles elicited from experts, we propose a Bayesian model based on the metalog distribution and a variant of the Dirichlet prior. We discuss the resulting hybrid expert elicitation protocol, which aims to characterize uncertainty in parameters by asking questions about observable quantities. We also compare and contrast this approach with parametric and predictive elicitation methods.
Avdelning/ar
- Centrum för miljö- och klimatvetenskap (CEC)
- BECC: Biodiversity and Ecosystem services in a Changing Climate
- Beräkningsvetenskap för hälsa och miljö
- MERGE: ModElling the Regional and Global Earth system
Publiceringsår
2024-02
Språk
Engelska
Publikation/Tidskrift/Serie
Statistics and Computing
Volym
34
Dokumenttyp
Artikel i tidskrift
Förlag
Springer
Ämne
- Probability Theory and Statistics
Nyckelord
- Bayesian analysis
- Expert knowledge elicitation
- Indirect inference
- Quantile-based distributions
- Quantile-parameterized distributions
Status
Published
Forskningsgrupp
- Computational Science for Health and Environment
ISBN/ISSN/Övrigt
- ISSN: 0960-3174