1. NCCU Academic Hub
  2. 商學院
  3. 統計學系
  4. 學位論文
Please use this identifier to cite or link to this item: https://ah.lib.nccu.edu.tw/handle/140.119/49593
DC FieldValueLanguage
dc.contributor.advisor郭訓志zh_TW
dc.contributor.author王政忠zh_TW
dc.contributor.authorWang,Jheng-Jhongen_US
dc.creator王政忠zh_TW
dc.creatorWang,Jheng-Jhongen_US
dc.date2006en_US
dc.date.accessioned2010-12-08T06:42:50Z-
dc.date.available2010-12-08T06:42:50Z-
dc.date.issued2010-12-08T06:42:50Z-
dc.identifierG0094354022en_US
dc.identifier.urihttp://nccur.lib.nccu.edu.tw/handle/140.119/49593-
dc.description碩士zh_TW
dc.description國立政治大學zh_TW
dc.description統計研究所zh_TW
dc.description94354022zh_TW
dc.description95zh_TW
dc.description.abstract變數選取方法已經成為各領域在處理多維度資料的工具。Zhou與Hwang在2005年，為了改善James-Stein positive part估計量(JS+)只能在完全模型(full model)與原始模型(origin model)兩者去做挑選，建立了具有Minimax性質同時加上門檻值的估計量，即James-Stein with Threshoding positive part估計量(JSWT+)。由於JSWT+估計量具有門檻值，使得此估計量可以在完全模型與其線性子集下做變數選取。我們想進一步了解如果將JSWT+估計量應用於線性迴歸分析時，藉由JSWT+估計具有門檻值的性質去做變數選取的效果如何？本文目的即是利用JSWT+估計量具有門檻值的性質，建立JSWT+估計量應用於線性迴歸模型變數挑選的流程。建立模擬資料分析，以可同時做係數壓縮及變數選取的LASSO方法與我們所提出JSWT+變數選取的流程去比較係數路徑及變數選取時差異比較，最後將我們提出JSWT+變數選取的流程對實際資料攝護腺癌資料(Tibshirani，1996)做變數挑選。則當考慮解釋變數個數小於樣本個數情況下，JSWT+與LASSO在變數選取的比較結果顯示，JSWT+表現的比較好，且可直接得到估計量的理想參數。zh_TW
dc.description.tableofcontents摘要 I\n謝辭 II\n圖表目錄 IV\n第一章 緒論 1\n第二章 文獻探討 3\n第三章 研究方法 5\n第一節 線性迴歸模型 5\n第二節 Minimax 與 Dominate 6\n第三節 James-Stein type Shrinkage 7\n第四節 Sclove+估計量 9\n第五節 James-Stein with Thresholding估計量(JSWT) 9\n第六節 JSWT+於迴歸問題之應用 12\n第四章 分析結果與討論 14\n第一節 模擬分析(設定真實係數三個非零) 14\n第二節 模擬分析(設定真實係數僅一個非零) 21\n第三節 JSWT+與LASSO參數挑選 26\n第四節 攝護腺癌資料分析 27\n第五章 結論與建議 29\n參考文獻 31\n附錄 33\n(I)設定真實係數八個皆非零(0.85) 33\n(II)設定真實係數八個皆為零 36zh_TW
dc.format.extent117657 bytes-
dc.format.extent118388 bytes-
dc.format.extent136582 bytes-
dc.format.extent141810 bytes-
dc.format.extent125254 bytes-
dc.format.extent163112 bytes-
dc.format.extent207216 bytes-
dc.format.extent269192 bytes-
dc.format.extent123586 bytes-
dc.format.extent120127 bytes-
dc.format.extent197111 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/pdf-
dc.language.isoen_US-
dc.source.urihttp://thesis.lib.nccu.edu.tw/record/#G0094354022en_US
dc.subjectJames-Stein估計量zh_TW
dc.subject變數選取zh_TW
dc.subject線性迴歸模型zh_TW
dc.subjectminimaxen_US
dc.subjectLASSOen_US
dc.titleJSWT+估計應用於線性迴歸變數選取之研究zh_TW
dc.titleVariable Selection Based on JSWT+ Estimator for Linear Regressionen_US
dc.typethesisen
dc.relation.referenceBaranchik, A.J. (1964) Multiple regression and estimation of the mean of a multivariate normal distribution. Technical Report 51, Department of Statistics, Stanford University Stanford .zh_TW
dc.relation.referenceBreiman, L. (1995) Better subset selection using the nonnegative garotte. Technnometrics,37,373-384zh_TW
dc.relation.referenceHocking, R. R. (1976) The analysis and selection of variables in linear regression. Biometrics. 32, 1-49zh_TW
dc.relation.referenceHoerl, A. E. and Kennard, R. W. (1970) Ridge regression: Biased estimation for non-orthogonal problems. Technometrics. 12,55-67zh_TW
dc.relation.referenceRichards, John A. (1999) An introduction James-Stein estimationzh_TW
dc.relation.referenceStein, C. (1956), \"Inadmissibility of the usual estimator for the mean of a multivariate distribution\", Proc. Third Berkeley Symp. Math. Statist. Prob., vol. 1, at 197-206zh_TW
dc.relation.referenceJames, W. & C. Stein (1961), \"Estimation with quadratic loss\", Proc. Fourth Berkeley Symp. Math. Statist. Prob., vol. 1, at 311-319zh_TW
dc.relation.referenceScolve,S.L.(1968).Improved estimators for voefficients in linear regression. J. Amer. Statist. Assoc. 63,597-606zh_TW
dc.relation.referenceStamey, T., Kabalin, J., McNeal, J., Johnstone, I., Freiha, F., Redwine, E. and Yang, N. (1989) Prostate specific antigen in the diagnosis and treatment of adenocarcinoma of the prostate, ii: Radical prostatectomy treated patients. J. Urol., 16, 1076-1083.zh_TW
dc.relation.referenceStein, C. (1981) Estimation of the mean of a multivariate normal distribution. Ann. Statist., 9, 1135-1151.zh_TW
dc.relation.referenceTibshirani, R. (1996) Regression shrinkage and selection via the lasso. J. R. Statist. Soc. B, 58, 267–288.zh_TW
dc.relation.referenceZou, H. and Hastie, T (2005) Regularization and variable selection via the elastic net. J. R. Statist. Soc. B. 67, Part 2, 301–320zh_TW
dc.relation.referenceZhou, H. H. and Hwang, J. T. G. (2003).Minimax estimation with thresholding. Technical report,Cornell Statistical Center.zh_TW
dc.relation.referenceZhou, H. H. and Hwang, J. T. G. (2005).Minimax estimation with thresholding. And its application to wavelet analysis. The Annals of Statistics. Vol. 33, No. 1, 101–125zh_TW
item.languageiso639-1en_US-
item.fulltextWith Fulltext-
item.grantfulltextopen-
item.cerifentitytypePublications-
item.openairetypethesis-
item.openairecristypehttp://purl.org/coar/resource_type/c_46ec-
Appears in Collections:學位論文
Files in This Item:
File Description SizeFormat
402201.pdf114.9 kBAdobe PDF2View/Open
402202.pdf115.61 kBAdobe PDF2View/Open
402203.pdf133.38 kBAdobe PDF2View/Open
402204.pdf138.49 kBAdobe PDF2View/Open
402205.pdf122.32 kBAdobe PDF2View/Open
402206.pdf159.29 kBAdobe PDF2View/Open
402207.pdf202.36 kBAdobe PDF2View/Open
402208.pdf262.88 kBAdobe PDF2View/Open
402209.pdf120.69 kBAdobe PDF2View/Open
402210.pdf117.31 kBAdobe PDF2View/Open
402211.pdf192.49 kBAdobe PDF2View/Open
Show simple item record

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.