Abstract
This paper describes how importance sampling can be applied to estimate likelihoods for spatio-temporal stochastic models of epidemics in plant populations, where observations consist of the set of diseased individuals at two or more distinct times. Likelihood computation is problematic because of the inherent lack of independence of the status of individuals in the population whenever disease transmission is distance-dependent. The methods of this paper overcome this by partitioning the population into a number of sectors and then attempting to take account of this dependence within each sector, while neglecting that between-sectors. Application to both simulated and real epidemic data sets show that the techniques perform well in comparison with existing approaches. Moreover, the results confirm the validity of likelihood estimates obtained elsewhere using Markov chain Monte Carlo methods.
Similar content being viewed by others
References
Cowles M.K. and Carlin B.P. 1996. Markov chain Monte Carlo convergence diagnostics: A comparative review. Journal of the American Statistical Society 91: 883–904.
Filipe J.A.N. and Gibson G.J. 1998. Studying and approximating spatiotemporal models for epidemic spread and control. Philiosophical Transactions Royal Society London B 353: 2153–2162.
Gibson G.J. 1997a. Investigating mechanisms of spatio-temporal epidemic spread using stochastic models. Phytopathology 87: 138–146.
Gibson G.J. 1997b. Markov Chain Monte Carlo methods for fitting and testing spatio-temporal stochastic models in plant epidemiology. Applied Statistics 46: 215–233.
Gibson G.J. and Austin E.J. 1996. Fitting and testing spatio-temporal stochastic models with application in plant epidemiology. Plant Pathology 45: 172–184.
Gibson G.J. and Renshaw E. 2001. Likelihood estimation for stochastic compartmental models using Markov chain methods. Statistics and Computing 11: 335–346.
Gottwald T.R., Gibson G.J., Garnsey S.M., and Irey M. 1999. Examination of the effect of aphid vector population composition on the spatial dynamics of citrus tristeza virus spread via stochastic modelling. Phytopathology 89: 603–608.
Marcus R., Svetlana F., Talpaz H., Salomon R., and Bar-Joseph M. 1982. On the spatial distribution of citrus tristeza virus disease. Phytoparasitica 12: 45–52.
O'Neill P.D. and Roberts G.O. 1999. Bayesian inference for partially observed stochastic epidemics. Journal of the Royal Statistical Society A 162: 121–129.
Propp J.G. and Wilson D.B. 1996. Exact sampling with coupled Markov chains and application to statistical mechanis. Random Structures Algorithms 9: 223–252.
Rand D.A. and Wilson H.B. 1995. Using spatio-temporal chaos and intermediate-scale determinism to quantify spatially-extended ecosystems. Proceedings Royal Society London B 259: 111–117.
Ripley B.D. 1987. Stochastic Simulation. Wiley, New York.
Roberts C.P. and Cassella G. 1999. Monte Carlo Statistical Methods. Springer, New York.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Marion, G., Gibson, G. & Renshaw, E. Estimating likelihoods for spatio-temporal models using importance sampling. Statistics and Computing 13, 111–119 (2003). https://doi.org/10.1023/A:1023200324137
Issue Date:
DOI: https://doi.org/10.1023/A:1023200324137