Towards a Bayesian framework for model validation

Ander Gray; Edoardo Patelli

doi:10.22725/ICASP13.347

Towards a Bayesian framework for model validation

Ander Gray, Edoardo Patelli

Civil And Environmental Engineering

Research output: Contribution to conference › Paper › peer-review

16 Downloads (Pure)

Abstract

In this paper we discuss some concepts and a methodology of a Bayesian framework for model validation under uncertainty, which produces a probabilistic value for a models validity and may be used in the design of”validation experiments. By using a stochastic metric as a measure of the distance between experiment and prediction, we update a validation distribution. We show this in practice using a simple numerical experiment and discuss the current shortcomings of the method. We finally discuss the role of information entropy in designing validation experiments.

Original language	English
Number of pages	8
DOIs	https://doi.org/10.22725/ICASP13.347
Publication status	Published - 26 May 2019
Event	13th International Conference on Applications of Statistics and Probability in Civil Engineering - Seoul, Korea, Republic of Duration: 26 May 2019 → 30 May 2019

Conference

Conference	13th International Conference on Applications of Statistics and Probability in Civil Engineering
Abbreviated title	ICASP 13
Country/Territory	Korea, Republic of
City	Seoul
Period	26/05/19 → 30/05/19

Keywords

Bayesian framework
uncertainty
model validation

Access to Document

10.22725/ICASP13.347

Gray-Patelli-ICASP2019-Towards-a-Bayesian-framework-for-model-validationAccepted author manuscript, 489 KB

Cite this

@conference{17dbab7f79234ec08b9bf9503cbc0977,

title = "Towards a Bayesian framework for model validation",

abstract = "In this paper we discuss some concepts and a methodology of a Bayesian framework for model validation under uncertainty, which produces a probabilistic value for a models validity and may be used in the design of”validation experiments. By using a stochastic metric as a measure of the distance between experiment and prediction, we update a validation distribution. We show this in practice using a simple numerical experiment and discuss the current shortcomings of the method. We finally discuss the role of information entropy in designing validation experiments.",

keywords = "Bayesian framework, uncertainty, model validation",

author = "Ander Gray and Edoardo Patelli",

year = "2019",

month = may,

day = "26",

doi = "10.22725/ICASP13.347",

language = "English",

note = "13th International Conference on Applications of Statistics and Probability in Civil Engineering, ICASP 13 ; Conference date: 26-05-2019 Through 30-05-2019",

}

TY - CONF

T1 - Towards a Bayesian framework for model validation

AU - Gray, Ander

AU - Patelli, Edoardo

PY - 2019/5/26

Y1 - 2019/5/26

N2 - In this paper we discuss some concepts and a methodology of a Bayesian framework for model validation under uncertainty, which produces a probabilistic value for a models validity and may be used in the design of”validation experiments. By using a stochastic metric as a measure of the distance between experiment and prediction, we update a validation distribution. We show this in practice using a simple numerical experiment and discuss the current shortcomings of the method. We finally discuss the role of information entropy in designing validation experiments.

AB - In this paper we discuss some concepts and a methodology of a Bayesian framework for model validation under uncertainty, which produces a probabilistic value for a models validity and may be used in the design of”validation experiments. By using a stochastic metric as a measure of the distance between experiment and prediction, we update a validation distribution. We show this in practice using a simple numerical experiment and discuss the current shortcomings of the method. We finally discuss the role of information entropy in designing validation experiments.

KW - Bayesian framework

KW - uncertainty

KW - model validation

UR - http://www.scopus.com/inward/record.url?scp=85070969329&partnerID=8YFLogxK

U2 - 10.22725/ICASP13.347

DO - 10.22725/ICASP13.347

M3 - Paper

T2 - 13th International Conference on Applications of Statistics and Probability in Civil Engineering

Y2 - 26 May 2019 through 30 May 2019

ER -

Towards a Bayesian framework for model validation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this