Skip to main content
Journal cover image

The effect of ambiguous prior knowledge on Bayesian model parameter inference and prediction

Publication ,  Journal Article
Rinderknecht, SL; Albert, C; Borsuk, ME; Schuwirth, N; Künsch, HR; Reichert, P
Published in: Environmental Modelling and Software
January 1, 2014

Environmental modeling often requires combining prior knowledge with information obtained from data. The robust Bayesian approach makes it possible to consider ambiguity in this prior knowledge. Describing such ambiguity using sets of probability distributions defined by the Density Ratio Class has important conceptual advantages over alternative robust formulations. Earlier studies showed that the Density Ratio Class is invariant under Bayesian inference and marginalization. We prove that (i) the Density Ratio Class is also invariant under propagation through deterministic models, whereas (ii)predictions of a stochastic model with parameters defined by a Density Ratio Class are embedded in a Density Ratio Class. These invariance properties make it possible to describe sequential learning and prediction under a unified framework. We developed numerical algorithms to minimize the additional computational burden relative to the use of single priors. Practical feasibility of these methods is demonstrated by their application to a simple ecological model.

Duke Scholars

Published In

Environmental Modelling and Software

DOI

ISSN

1364-8152

Publication Date

January 1, 2014

Volume

62

Start / End Page

300 / 315

Related Subject Headings

  • Environmental Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Rinderknecht, S. L., Albert, C., Borsuk, M. E., Schuwirth, N., Künsch, H. R., & Reichert, P. (2014). The effect of ambiguous prior knowledge on Bayesian model parameter inference and prediction. Environmental Modelling and Software, 62, 300–315. https://doi.org/10.1016/j.envsoft.2014.08.020
Rinderknecht, S. L., C. Albert, M. E. Borsuk, N. Schuwirth, H. R. Künsch, and P. Reichert. “The effect of ambiguous prior knowledge on Bayesian model parameter inference and prediction.” Environmental Modelling and Software 62 (January 1, 2014): 300–315. https://doi.org/10.1016/j.envsoft.2014.08.020.
Rinderknecht SL, Albert C, Borsuk ME, Schuwirth N, Künsch HR, Reichert P. The effect of ambiguous prior knowledge on Bayesian model parameter inference and prediction. Environmental Modelling and Software. 2014 Jan 1;62:300–15.
Rinderknecht, S. L., et al. “The effect of ambiguous prior knowledge on Bayesian model parameter inference and prediction.” Environmental Modelling and Software, vol. 62, Jan. 2014, pp. 300–15. Scopus, doi:10.1016/j.envsoft.2014.08.020.
Rinderknecht SL, Albert C, Borsuk ME, Schuwirth N, Künsch HR, Reichert P. The effect of ambiguous prior knowledge on Bayesian model parameter inference and prediction. Environmental Modelling and Software. 2014 Jan 1;62:300–315.
Journal cover image

Published In

Environmental Modelling and Software

DOI

ISSN

1364-8152

Publication Date

January 1, 2014

Volume

62

Start / End Page

300 / 315

Related Subject Headings

  • Environmental Engineering