臺灣博碩士論文加值系統

利用重覆捕取實驗估計母體總數在生態學、流行病學方面之應用相當廣泛。早期重覆捕取實驗一般均假設樣本間獨立，然而樣本間在許多實際數據中皆顯示相關性存在，目前處理樣本間相關性的方法，主要為對數線性模型（Log-linear model, Cormack, 1989）及共變異係數方法（Coefficient of Covariation, Chao & Tsay, 1998）。根據文獻，利用對數線性模型，必須假設高階交互作用不存在，但事實上此一強烈假設，會導致母體總數估計量產生偏差。本論文主要探討當捕取機率受時間效應及行為反應影響時，對數線性模型應如何給予合適的假設，並以共變異係數量化樣本間的相關性，同時發現經由合適假設下之估計量與條件最大概似估計量相同。我們將此理論應用於實例分析，採用V. Reid 所收集的一組老鼠（Deer Mouse）數據，合適假設下之估計量與條件最大概似估計量一致。再針對捕取機率受行為反應影響模擬，比較過去三種估計量，由模擬結果顯示，本文所提出的估計量亦與條件最大概似估計量一致，且比傳統對數線性模型的估計量較佳。因此，對數線性模型假設高階交互作用不存在的一般做法，當樣本存在相關時，有待修正及進一步探討。

目錄
第一章 緒論 1
第二章 符號說明及介紹樣本相關 3
2.1 符號說明……………………………………………….………………3
2.2 共同假設、模式簡介………………………………………………….4
2.3 共變異係數簡介……………………………………….…………..…..5
2.4 對數線性模型簡介…………………………………….…………..…..7
第三章 動物行為模型母體總數估計之文獻回顧 10
3.1 最大概似估計量與條件最大概似估計量……...…………………….10
3.2 傳統對數線性模型求條件最大概似估計量……...…………….........13
第四章 適合對數線性模型的限制式 16
4.1 Mtb模型……………………………………………..……………….…16
4.2 Mb模型………...……………………………………………..…...........20
第五章 樣本間相關性 24
5.1 Mtb模型……………………….……………….…..…………………...24
5.2 Mb模型……………….……………………..….……………….…..….27
5.3 比較Mh、Mb與Mbh的二階ccv圖型 ………………………………..28
第六章 實例及模擬分析 31
6.1 模擬條件………………………………………………………..….…..31
6.2 實例分析……….……...……………………………………………….32
第七章 討論及未來研究方向 34
7.1 討論…………………………………………………….………………34
7.2 未來研究方向……………………………………………………….....35
附錄 36
參考文獻 38

參考文獻
[1] Agresti, A. (1990). Categorical Data Analysis. New York, Wiley.
[2] Bishop, Y.M.M., Fienberg, S.E. , and Holland P.W. (1975). Discrete Multivariate Analysis：Theory and Practice. Combridge, MA：The MIT Press
[3] Chao, A. and Tsay, P.K. (1998). A Sample Coverage Approach to Multiple-System Estimation With Application to Census Undercount. Journal of American Statistical Association, 93, 283-293.
[4] Chao, A., Chu, W. and Hsu, C.H. (2000). Inference for Capture-Recapture Experiments When Both Time and Behavioral Response Affect Capture Probabilities. Biometrics, 56, 427-433.
[5] Chao, A. (2001). An Overview of Closed Capture-Recapture Models. Journal of Agricultural, Biological and Environmental Statistics, 6, 158-175
[6] Chao, A., Tsay, P. K., Lin, S.H., Shau, W.Y. and Chao, D.Y. (2001). Tutorial in Biostatistics: the Applications of Capture-Recapture Models to Epidemiological Data. Statistics in Medicine, 20, 3123-3157.
[7] Cormack , R.M. (1989). Loglinear Models for Capture-Recapture Estimation. Biometrics 36, 149-153.
[8] Darroch, J. N. (1958). The Multiple Recapture Census I：Estimation of a Closed Population. Biometrika 45, 343-359.
[9] Darroch, J. N. Fienberg, S. E., Glonek, F.V. and Junker, B.W. (1993). A Three-Sample Multiple-Recapture Approach to Census Population Estimation with Heterogeneous Catchability . Journal of the American Statistical Association 88, 1137-1148.
[10] Fienberg, S. E. (1972). The Multiple Recapture Census for Closed Populations and Incomplete 2k Contingency Tables. Biometrika 59, 591-603.
[11] Otis, D.L., Burnham, K.P., White, G.C., Anderson, D.R. (1978). Statistical Inference from Capture Data on Closed Animal Populations. Wildlife Monographs 62, 1-135.
[12] Pollock, K. H.（1976）. Building Methods of Capture-Recapture Experiment. The Statistician 25, 253-260.
[13] Pollock , K.H. (1991). Modeling Capture, Recapture, and Removal Statistics for Estimation of Demographic Parameters for Fish and Wildlife Population：Past, Present, and Future. Journal of the American Statistical Association 86, 225-238.
[14] Rasch, G. (1961). On General Laws and the Meaning of Measurement in Psychology . In Proceeding of The Fourth Berkeley Symposium on Mathematical Statistics and Probability. 321-333, J. Neyman（Ed）, University of California Press.
[15] Sanathanan, L. (1972). Estimating the Size of a Multinomial Population. The Annals of Mathematical Statistical 43, 142-152.
[16] Sanathanan, L. (1977). Estimating the Size of a Truncated Sample. Journal of the American Statistical Association 72, 669-672.
[17]Stegelman, W. (1983). Explanding the Rasch Model to A General Model Having More than one dimension. Psychometrika 48, 259-267.
[18]蔡培癸（1997）。重覆捕取實驗中對數線性模式分析與樣本函蓋方法之比較。[清華大學統計研究所博士論文]
[19]李丕強（1999）。具時間效應與行為反應之重覆捕取模式之模擬分析。[清華大學統計研究所碩士論文]