時間空間模型對北台灣腸病毒高發病率地區的預測

Time And Space Model Prediction Of The High Incidence Area Of Northern Taiwan Enterovirus

李曉芬(Lee, Hsioafen)

指導教授 ： 林培生

國立中正大學/理學院/數學系統計科學研究所/碩士(2012年)

摘要

在本論文中，我們將利用時間序列模型找出月腸病毒資料的規律性和可預測性，接著使用可逆跳躍式馬可夫鏈蒙地卡羅法(Reversible Jump Markov Chain Monte Carlo algorithm)，
透過階層卜瓦松廣義線性模型(Hierarchical Poisson generalized linear model)對研究區域內的群聚個數與位置進行貝氏理論的分析，
並利用 Metropolis-Hasting alogrithm 對模型內的隨機因素進行更新。最後，利用時間序列模型中的季節性自我迴歸整合移動平均模型預測北台灣 2009 年各個月份腸病毒資料的群聚現象。

關鍵字

時間空間模型

並列摘要

In this paper, we will use the time series model to identify the regularity and predictability of the month enterovirus information, then use the reversible jump Markov chain Monte Carlo method (Reversible the Jump of Markov the Chain the Monte Carlo algorithm) through the class BUPoisson generalized linear model (the Hierarchical the Poisson generalized linear model) analysis of the Bayesian theory of cluster number and location within the study area, and use the Metropolis-Hasting the alogrithm on random factors in the model update. Finally, the use of time series models in seasonal autoregressive integrated moving average model to predict the clustering phenomenon of the northern Taiwan enterovirus data for each month of 2009.

並列關鍵字

Reversible Jump Markov Chian Monte Carlo alorgithm

參考文獻

Besag, J. and Newell, J. (1991). The detection of clusters of rare diseases.

Journal of the Royal Statistical Society A 154, 143-155.

Clayton, D. and Kaldor, J. (1987). Empirical Bayes estimates of age-standardized relative risks for use in disease mapping. Biometrics 43, 671-681.

Gelman, A., Carlin, J.B., Stern, H.S. and Rubin, D.B. (1995).

Gangnon, R.E. and Clayton, M.K. (2000). Bayesian detection and modeling of spatial disease clustering. Biometrics 56, 922-935.