# 臺灣博碩士論文加值系統

(35.153.100.128) 您好！臺灣時間：2022/01/22 06:44

:::

### 詳目顯示

:

• 被引用:1
• 點閱:433
• 評分:
• 下載:94
• 書目收藏:1
 有關使用貝氏方法分析混合模型的相關文獻中, 目前尚未發現有對多變量 t 分配的混合模型做深入探討的文章, 我們擬對其做一些較深入的探討。 當資料可以被分成 g 群, 且其中一群或多群的觀察值有較常態分配長的尾端時, 使用多變量 t 分配的混合模型是多變量常態分配的混合模型的穩健性延伸。 由於對混合模型使用貝氏方法做推論並不允許無訊息的事前分配, 所以我們採用對參數提供微弱先驗訊息的事前分配。 在參數估計方面, 我們擬用最大概似估計法與貝氏方法做參數估計及未來個體的預測分析; 關於貝氏計算方法, 採用MCMC做參數估計, 並就MCMC抽樣的結果診斷收斂性。 最後, 以一個實際的例子藉由比較貝氏方法與最大概似估計法對未來個體未觀察到的部分之預測的精確度及對部分觀察到的未來個體之分類的正確性來說明貝氏方法優於最大概似估計法。
 Finite mixture models using the multivariate t distribution have been provided as a robust extension of normal mixtures. In this paper, from a Bayesian point of view, we consider estimation of parameters, prediction of future values and classification of partially observed future vectors for the t mixture model. The specification of prior distributions are weakly informative, which may or may not be data-dependent, and proper to avoid causing impossible posterior distributions. For parameter estimation, ECM and ECME algorithms are derived based on the observed data and partially observed future vector. Markov chain Monte Carlo (MCMC) schemes are also developed to obtain more accurate Bayesian inference for parameters. The advantage of the Bayesian approach over the maximum likelihood (ML) method are demonstrated via a real data.
 1 Introduction …………………………………………………… 1 2 Finite t mixture model ……………………………………… 3 3 Parameter estimation based on and partially observed individual ……………………………………………………… 7 4 Bayeian inference using Markov chain Monte Carlo method ……………………………………………………………………… 13 5 Conditional prediction and Bayesian classification … 18 6 Illustration …………………………………………………… 20 7 Concluding remarks …………………………………………… 27 Appendix …………………………………………………………… 28 Reference ………………………………………………………… 37
 Anscombe, F. J. (1967) Topics in the investigation of linearrelations fitted by the method of least squares. Journal ofthe Royal Statistical Society, series B 29: 1-52.Brooks, S. P. and Gelman, A. (1998) General methods formonitoring convergence of iterative simulations. Journal ofComputational and Graphical Statistics} 7: 434-455.Campbell, N. A. and Mahon, R. J. (1974) A multivariate study ofvariation in two species of rock crab of genus Leptograpsus.Australian Journal of Zoology} 22: 417-425.van Dyk, D. A. Meng, X. L. and Rubin, D. B. (1995) Maximumlikelihood estimation via the ECM algorithm: computing theasymptotic variance. Statistica Sinica} 5: 55-75.Dempster, A. p., Laird, N. M., and Rubin, D. B. (1977) Maximumlikelihood from incomplete data via the EM algorithm (withdiscussion). Journal of the Royal Statistical Society, seriesB 39: 1-38.Diebolt, J. and Robert, C. P. (1994) Estimation of finitemixture distributions through Bayesian sampling. Journal ofthe Royal Statistical Society, series B 56: 363-375.Geisser, S. (1974) A predictive approach to the random effectmodel. Biometrika 61: 101-107.Geisser, S. (1975) The predictive sample reuse method withapplications. Journal of the American Statistical Association70: 320-328.Gelman, A. and Rubin, D. B. (1992) Inference from iterativesimulation using multiple sequences. Statistical Science 7:457-511.Gelman, A., Roberts, G. and Gilks, W. (1995) EfficientMetroplis jumping rules. In Bayesian Statistics 5}, ed. J. M.Bernardo, J. O. Berger, A. P. Dawid and A. F. M. Smith. NewYork: Oxford University Press.Hawkins D. M. (1981) A new test for multivariate normality andHomoscedasticity. Technometrics} 23: 105-110.Lee, J. C. and Geisser, S. (1975) Applications of growth curveprediction. Sankhya Ser A 37: 239-256.Liu, C. H. and Rubin, D. B. (1994) The ECME algorithm: A simpleextension of EM and ECM with faster monotone convergence.Biometrika 81: 633-648.Liu, C. H. (1995) Missing data imputation using the multivariatet distribution. Journal of multivariate analysis 53: 139-158.Liu, C. H. and Rubin, D. B. (1995) ML estimation of the tdistribution using EM and its extensions, ECM and ECME.Statistica Sinica 5: 19-39.McLachlan, G. J. and Peel, D. (1998) Robust cluster analysis viamixtures of multivariate \$t\$-distribution. In Lecture Notes inComputer Science, 1451, A. Amin, D. Dori, P. Pudil, and H.Freeman (Eds.). Berlin: Springer-Verlag, pp. 658-666.Meng, X. L. and Rubin, D. B. (1991) Using EM to obtainasymptotic variance-covariance matrices: The SEM algorithm.Journal of the American StatisticalAssociation} 86: 899-909.Meng, X. L. and Rubin, D. B. (1993) Maximum likelihoodestimation via the ECM algorithm: A generalframework. Biometrika 80: 267-278.Pearson, K. (1894) Contributions to the theory of mathematicalevolution. Philosophical Transactions of the Royal Society ofLondon A 185: 71-110.Peel, D. and McLachlan, G. J. (2000) Robust mixture modellingusing the t distribution. Statistics and Computing 10: 339-348.Rao, C. R. (1948) The utilization of multiple measurements inproblems of biological classification. Journal of the RoyalStatistical Society, series B} 10: 159-203.Relles, D. A. and Rogers, W. H. (1977) Statistics are fairlyrobust estimators of location. Journal of the AmericanStatistical Association 72: 107-111.Ripley, B. D. (1996) Pattern recognition and neural networks.Cambridge: Cambridge University Press.Richardson, S. and Green, P. J. (1997) On Bayesian analysis ofmixtures with an unknown number of components. Journal of theRoyal Statistical Society, series B 59: 731-792.Render, R. A. and Walker, H. F. (1984) Mixture densities,maximum likelihood and the EM algorithm. SIAM Review 26:195-239.Stephens, M. A. (1997) Bayesian method for mixtures of normaldistributions Ph.D. thesis, University of Oxford.Stephens, M. A. (2000) Dealing with label switching in mixturemodels. Journal of the Royal Statistical Society, series B 62:795-809.Tiao, G. C. (1967) Discussion on "Topics in the investigationof linear relations fitted by the method of least squares."Journal of the Royal Statistical Society, series B 29: 44-47.
 電子全文
 國圖紙本論文
 推文當script無法執行時可按︰推文 網路書籤當script無法執行時可按︰網路書籤 推薦當script無法執行時可按︰推薦 評分當script無法執行時可按︰評分 引用網址當script無法執行時可按︰引用網址 轉寄當script無法執行時可按︰轉寄

 1 年齡縮減之不完全預防維護模型參數估計 2 具自我相關性誤差的線性混合效應模型與有限t分佈混合模型之研究特論

 1 尤雅正、王立敏、李建賢（1998）‧急診部門與暴力事件‧臨床醫學，41(5)，364-371。 2 王湘如（1992）‧國軍某醫院內外科住院病患對護理服務滿意度之研究‧國防醫學，14(3)，293-299。 3 沈志仁、張素凰（1993）‧精神分裂患者主要照顧家屬的需要及其相關因素探討‧中華心理衛生學刊，6(1)，49-56。 4 林貴滿（1999）‧台灣中部地區急診病患需求滿意度及影響因素探討‧弘光學報，34，21-45。 5 胡勝川（1995）‧急診室護理人員醫療體系的守護神急診醫師‧臨床醫學，35 (6)，383-389。 6 陳淑華（1990）‧兒科一般病房家屬需求之初步探討‧長庚護理，1(2)，24-29。 7 陳潭（1994）‧護理人員的人格特質與工作滿意度之相關研究‧東海學報，35，117-133。 8 許國正、翁麗雀（1999）‧灼傷患童父母需求及其影響因素之探討‧長庚護理，10 (3)，1-11。 9 黃瑞美、錢端蘭（1997）‧急救室病患家屬與護理人員對自覺需求之探討‧榮總護理，14 (1)，84-93。 10 劉長安、蘇婉麗（1998）‧某醫學中心住院患者家屬對醫院需求及其滿意度之探討‧護理雜誌，45 (2)，47-58。 11 穆佩芬（1994）‧家庭護理之理論及臨床應用‧榮總護理，12（4），244-251。 12 饒雅萍（1988）‧加護病房病患家屬需求及其影響因素之探討‧護理雜誌，35 (1)，23-36。 13 繆珣（1994） ‧影響急診病患對急診服務滿意度因素之探討‧榮總護理，11(4)，348-360。

 1 具群體變異數且為一般自相關共變異數結構之生長曲線模型 2 聯立方程模型的Mallow兩階段截斷平均數 3 利用廣義交叉驗證法決定板條插補法之參數及三維超音波影像的無母數影像細胞單元分群法 4 一個新自相關性製程監控方法之研究 5 監控多變量製程變異性增加之管制圖 6 分位數信賴區間的估計法 7 多層解析混合自迴歸樹狀空間模型 8 利用佇列系統之M/G/m模型模擬基地台顧客之進入與轉移並估算平衡狀態下顧客被拒絕之機率 9 遭受隨機干擾之馬可夫過程於可靠度分析上的應用 10 半競爭風險下雙樣本之比較 11 多重路徑模式的邏輯斯迴歸分析 12 倖存分析之訊息設限問題之文獻回顧 13 一個新相關性製程變異監控方法之研究 14 運用統計方法與微陣列技術探討放射線照射後之未同步化腦腫瘤細胞內基因表現 15 隨機過程在線性迴歸ME模型下的估計問題

 簡易查詢 | 進階查詢 | 熱門排行 | 我的研究室