Fitting the Bartlett–Lewis rainfall model using Approximate Bayesian Computation

被引：4

作者：

Aryal N.R. ^{[1
]}

Jones O.D. ^{[2
]}

机构：

[1] School of Mathematics and Statistics, University of Melbourne

[2] School of Mathematics, Cardiff University

来源：

Mathematics and Computers in Simulation | 2020年 / 175卷

关键词：

Approximate Bayesian Computation; Bartlett–Lewis process; Generalised method of moments; Markov Chain Monte Carlo; Rainfall; Simulation;

D O I：

10.1016/j.matcom.2019.10.018

中图分类号：

学科分类号：

摘要：

The Bartlett–Lewis (BL) rainfall model is a stochastic model for the rainfall at a single point in space, constructed using a cluster point process. The cluster process is constructed by taking a primary/parent process, called the storm arrival process in our context, and then attaching to each storm point a finite secondary/daughter point process, called a cell arrival process. To each cell arrival point we then attach a rain cell, with an associated rainfall duration and intensity. The total rainfall at time t is then the sum of the intensities from all active cells at that time. Because it has an intractable likelihood function, in the past the BL model has been fitted using the Generalised Method of Moments (GMM). The purpose of this paper is to show that Approximate Bayesian Computation (ABC) can also be used to fit this model, and moreover that it gives a better fit than GMM. GMM fitting matches theoretical and observed moments of the process, and thus is restricted to moments for which you have an analytic expression. ABC fitting compares the observed process to simulations, and thus places no restrictions on the statistics used to compare them. The penalty we pay for this increased flexibility is an increase in computational time. © 2019 International Association for Mathematics and Computers in Simulation (IMACS)

引用

页码：153 / 163

页数：10

共 18 条

[1]

Aitken A.C., On least squares and linear combination of observations, Proc. Roy. Soc. Edinburgh, 55, pp. 42-48, (1936)

[2]

Aryal N., Jones O., Fitting the Bartlett-Lewis rainfall model using approximate Bayesian computation, MODSIM2017, 22nd International Congress on Modelling and Simulation, pp. 1579-1585, (2017)

[3]

Beaumont M., Cornuet J.-M., Marin J.-M., Robert C., Adaptive approximate Bayesian computation, Biometrika, 96, 4, pp. 983-990, (2009)

[4]

Beaumont M., Zhang W., Balding D., Approximate Bayesian computation in population genetics, Genetics, 162, pp. 2025-2035, (2002)

[5]

Cowpertwait P., Isham V., Onof C., Point process models of rainfall: developments for fine-scale structure, Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci., 463, pp. 2569-2587, (2007)

[6]

Kaczmarska J., Further development of Bartlett-Lewis models for fine-resolution rainfall: Tech. rep. 312, (2011)

[7]

Kaczmarska J., Isham V., Onof C., Point process models for fine-resolution rainfall, Hydrol. Sci. J., 59, 11, pp. 1972-1991, (2014)

[8]

Marjoram P., Molitor J., Plagnol V., Tavare S., Markov chain Monte Carlo without likelihoods, Proc. Nat. Acad. Sci., 100, pp. 15324-15328, (2003)

[9]

McFadden D., A method of simulated moments for estimation of discrete response models without numerical integration, Econometrica, 57, pp. 995-1026, (1989)

[10]

Pakes A., Pollard D., Simulation and the asymptotics of optimization estimators, Econometrica, 57, pp. 1027-1057, (1989)

← 1 2 →