本文將貝氏模型平均法做一改良，提出模型漫步演算法以遞迴搜尋的方式選取模型，模擬結果顯示，在一般線性迴歸模型下，其平均被遺漏模型的後驗機率總和比傳統奧坎氏視窗法中所有遺漏的模型之後驗機率總和低；另外在選用不當的初始模型時，與使用較佳初始模型相較，模型漫步演算法所多耗費的計算量遠比奧坎氏視窗法少，且遺漏的模型也較少，亦即我們提出的演算法較不受限於初始模型的選擇。另外，配合吉比氏抽樣法將模型漫步演算法應用在具 AR(1) 誤差模型之長時期追蹤資料迴歸模型中，並將其應用在颱風降雨量之預測上。

In this thesis, we propose a new recursive algorithm, namely the model walking algorithm, to modify the widely used Occam''s window method in Bayesian model averaging procedure. It is verified, by simulation, that in the regression models, the proposed method is much more efficient in terms of computing time and the selected candidate models. Moreover, it is not sensitive to the initial models. We then apply Bayesian model averaging to the multiple longitudinal regression models with AR(1) random errors within subjects. Gibbs sampling method together with the model walking algorithm are employed. The proposed method is also successfully used to make rainfall prediction based on typhoon data in Taipei, Taiwan.

[1] Raftery, A. E., Balabdaoui, F., Gneiting, T., and Polakowski, M. (2003). Using Bayesian model averaging to calibrate forecast ensembles. Technical Report No. 440, Department of Statistics, University of Washington.
[2] Barnard, G. A. (1963). New methods of quality control. Journal of the Royal Statistical Society: Series A 126, 255-258.
[3] Chib, S. (1993). Bayes regression with autoregressive errors: A Gibbs sampling approach. Journal of Econometrics 58, 275-294.
[4] Clyde, M., DeSimone, H., and Parmigiani, G (1996). Prediction via orthoganalized model mixing. Journal of the American Statistical Association 91, 1197-1208.
[5] Collins, L. M. and Horn, J. L. (eds.) (1991). Best Methods for the Analysis of Change. Washington, DC: America Psychological Association.
[6] Cox, D. R. and Oakes, D. (1984). Analysis of Survival Data. Chapman and Hall, London.
[7] Dale, A. and Davies, R. B. (eds.) (1994). Analyzing Social and Political Change: A Casebook of Methods. London: Sage.
[8] Diggle, P. J. (1990). Time Series: a Biostatistical Introduction. Oxford University Press, Oxford.
[9] Draper, D. (1995). Assessment and propagation of model uncertainty (with discussion). Journal of the Royal Statistical Society series B 57, 45-97.
[10] Dutilleul, P. and Pinel-Alloul, B. (1996). A doubly multivariate model for statistical analysis of spatio-temporal environmental data. Environmetrics 7, 551-565.
[11] Gottman, J. M. (ed.) (1995). The Analysis of Change. Mahwah, NJ: Lawrence Erlbaum.
[12] Heitjan, D. F. and Sharma, D. (1997). Modelling repeated-series longitudinal data. Statistics in Medicine 16, 347-355.
[13] Kass, R. E. and Raftery, A. E. (1995). Bayes factors. Journal of the American Statistical Association 90, 773-795.
[14] Leamer, E. E. (1978). Specification Searches. Wiley, New York.
[15] Clyde, M. and DeSimone-Sasinowska, H. (1997). Accounting for model uncertainty in Poisson regression models: Does particulate matter? Technical Report March 10, Institute of Statistics and Desicion Sciences, Duke University, USA.
[16] Madigan, D. and Raftery, A. E. (1991). Model selection and accounting for model uncertainty in graphical models using Occam’s window. Technical Report No. 213, Department of Statistics, University of Washington.
[17] Madigan, D. and York, J. (1995). Bayesian graphical models for discrete data. International Statistical Review 63, 215-232.
[18] Montgomery, D. C., Peck, E. A., and Vining, G. G. (2001). Introduction to Linear Regression Analysis. Wiley, New York, 3rd ed.
[19] Raftery, A. E. (1996). Approximate Bayes factors and accounting for model uncertainty in generalized linear models. Biometrika 83, 251-266.
[20] Raftery, A. E., Madigan, D., and Hoeting, J. A. (1997). Bayesian model averaging for linear regression models. Journal of the American Statistical Association 92, 179-191.
[21] Raftery, A. E., Madigan, D. M., and Volinsky C. T. (1996). Accounting for model uncertainty in survival analysis improves predictive performance (with discussion). Bayesian Statistics 5, 323-349.
[22] Roberts, H. V. (1965). Probabilistic prediction. Journal of the American Statistical Association 60, 50-62.
[23] Viallefont, V., Raftery, A. E., and Richardson, S. (2001). Variable selection and Bayesian model averaging in epidemiological case-control studies. Statistics in Medicine 20, 3215-3230.
[24] 曾印堂 (2006)。台灣地區颱風降雨量預測之長時間追蹤資料迴歸模型。國立中央大學統計研究所碩士論文。
[25] 葉天降、樊采虹與李昀寰 (2001)。台灣地區颱風降水之迴歸預測(一) 台北颱風降水線性迴歸預測模式。大氣科學,29,77-79。