在時空隨機效應模型下，Cressie and Katzfuss (2011) 對最大概似估計的解提出有效率的數值解法。本論文進一步探討此模式的選模問題，藉由參數設限的技巧，達到簡化模型的目的。此處我們考慮三類不同的參數設限條件：第一類是對迴歸係數的設限，藉此可以達到選取重要解釋變數的目的；第二類考慮對變異數參數的設限，藉由此方式可達到選取隨機效應的目的；第三類考慮模型中與時空訊息相關的參數設限，其主要目的是為了選取時空上的相關結構。並在不同的模式設定下，我們會以電腦模擬進行討論。從模擬結果中發現設限最大概似估計都有不錯的表現，且所選取的隨機效應時空模式能提供有效的時空預測。

第一章緒論 1
第二章時空隨機效應模式 4
第三章參數估計和模式選取方法 8
第四章預測模型選取評量準則 19
第五章模擬研究 21
第六章結論 33
參考文獻 34

[1] Akaike, H. (1973). Information theory and an extension of maximum likelihood principle. In Second international symposium on information theory , eds. Petrov, B. N. and Csaki, F.
[2] Bondell, H. D., Krishna, A., & Ghosh, S. K. (2010). Joint variable selection for fixed and random effects in linear mixed effects models. Biometrics, 66(4), 1069-1077.
[3] Cressie, N. and Johannesson, G. (2008), Fixed rank kringing for very large spatial data sets. Journal of the Royal Statistical Society , Series B 70, 20926
[4] Cressie, N., Shi, T. and Kang, E. L. (2010), Fixed rank ltering for spatial-temporal data.Journal of Computational and Graphical Statistics, 19, 724-745.
[5] Dempster, A. P., Laird, N. M. and Rubin, D. B. (1977) Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society , Series B 39, 138.
[6] Fan, J. and Li, R. (2001). Variable selection via nonconcave penalized likelihood and its oracle properties. J. Amer. Statistic. Assoc. 96 13481360. MR1946581
[7] Kalman, R. (1960) A new approach to linear filtering and prediction problems. Journal of Basic Engineering 82, 3545.
[8] Katzfuss, M., & Cressie, N. (2011). Spatial-temporal smoothing and EM estimation for massive remotesensing data sets. Journal of Time Series Analysis , 32(4), 430-446.
[9] Mardia, K., Goodall, C., Redfern, E. and Alonso, F. (1998) The kringed Kalman filter. Test 7, 21782.
[10] Shumway, R. and Stoffer, D. (1982) An approach to time series smoothing and forecasting using the EM algorithm. Journal of Time Series Analysis 3, 25364.
[11] Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statistics 6, 461-464.
[12] Zou, H. (2006). The adaptive lasso and its oracle properties. Journal of the American Statistical Association 101, 1418-1429.