{"created":"2023-05-15T12:16:50.144186+00:00","id":320,"links":{},"metadata":{"_buckets":{"deposit":"16d979cf-9880-4111-9488-b387772a62a0"},"_deposit":{"created_by":3,"id":"320","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"320"},"status":"published"},"_oai":{"id":"oai:tuis.repo.nii.ac.jp:00000320","sets":["1:4:37:105"]},"author_link":["1280","1281","1282"],"control_number":"320","item_1701328008552":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"東京情報大学","subitem_publisher_language":"ja"}]},"item_1_biblio_info_14":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2004-09-30","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicPageEnd":"14","bibliographicPageStart":"9","bibliographicVolumeNumber":"8","bibliographic_titles":[{"bibliographic_title":"東京情報大学研究論集","bibliographic_titleLang":"ja"}]}]},"item_1_creator_6":{"attribute_name":"著者名(日)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"内田, 治","creatorNameLang":"ja"},{"creatorName":"ウチダ, オサム","creatorNameLang":"ja-Kana"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Uchida, Osamu","creatorNameLang":"en"}]}]},"item_1_creator_7":{"attribute_name":"著者名よみ","attribute_type":"creator","attribute_value_mlt":[{"nameIdentifiers":[{}]}]},"item_1_creator_8":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"nameIdentifiers":[{}]}]},"item_1_description_1":{"attribute_name":"ページ属性","attribute_value_mlt":[{"subitem_description":"P(論文)","subitem_description_type":"Other"}]},"item_1_description_11":{"attribute_name":"抄録(日)","attribute_value_mlt":[{"subitem_description":"本研究は、データを統計的に解析する方法論のひとつであるロジスティック回帰分析に関するものである。ロジスティック回帰分析において想定したモデルの適合度を評価する際に用いられるHosmer-Lemeshow検定の問題点を、人工的に作成した具体的な数値例によって明らかにした。さらに、この問題点を修正した新たな適合度指標を提案した。提案した適合度指標の実用性については、従来から提案されているモデルの対数尤度、Cox & Snell のR2値、NagelkerkeのR2値と比較して、整合性があることを確認した。また、本研究で提案している適合度指標は、Hosmer-Lemeshow検定の改善という観点から考え出したものであるが、ロジスティック回帰分析における寄与率R2が通常の回帰分析(OLS)で得られる寄与率に比べて低い値が得られやすく、モデルの信頼性を評価する際に、実用の場面では使いにくいという問題点の解消にも役立つことを報告する。","subitem_description_language":"ja","subitem_description_type":"Other"}]},"item_1_description_12":{"attribute_name":"抄録(英)","attribute_value_mlt":[{"subitem_description":"This study is concerned with logistic regression analysis which is a method of statistical dataanalysis. In this research, the problem of Hosmer-Lemeshow test used in logistic regression analysis for the purpose of evaluating the fitness of model was clarified by some numerical examples made artificially. In addition, a new measurement of fitness that corrected Hosmer-Lemeshow test was proposed. It was confirmed there was coordination with log-likelihood, Cox & Snell-R2,Nagelkerke-R2,which are usual measurements in logistic regression analysis. Moreover, it was found that report this new measurement is useful for the cancellation of the problem that contribution rate in logistic regression analysis is of no practical use at evaluating the reliability of model because their values are lower than contribution rate in ordinary least squares.","subitem_description_language":"en","subitem_description_type":"Other"}]},"item_1_description_17":{"attribute_name":"URL","attribute_value_mlt":[{"subitem_description":"http://www.iic.tuis.ac.jp/edoc/journal/ron/r8-1-2/index.html","subitem_description_type":"Other"}]},"item_1_source_id_13":{"attribute_name":"雑誌書誌ID","attribute_value_mlt":[{"subitem_source_identifier":"AA11155514","subitem_source_identifier_type":"NCID"}]},"item_1_text_10":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_language":"en","subitem_text_value":"Tokyo University of Information Sciences"}]},"item_1_text_9":{"attribute_name":"著者所属(日)","attribute_value_mlt":[{"subitem_text_language":"ja","subitem_text_value":"東京情報大学"}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2004-09-30"}],"displaytype":"detail","filename":"KJ00000681787.pdf","filesize":[{"value":"955.6 kB"}],"format":"application/pdf","license_note":"TUIS","licensetype":"license_note","mimetype":"application/pdf","url":{"url":"https://tuis.repo.nii.ac.jp/record/320/files/KJ00000681787.pdf"},"version_id":"11ac1834-c578-4e52-82b1-746ce94729c8"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ロジスティック回帰","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"適合度","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"Hosmer-Lemeshow検定","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"寄与率","subitem_subject_language":"ja","subitem_subject_scheme":"Other"},{"subitem_subject":"相関係数","subitem_subject_language":"ja","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"departmental bulletin paper","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"ロジスティック回帰分析におけるモデルの適合度指標に関する考察と提案","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ロジスティック回帰分析におけるモデルの適合度指標に関する考察と提案","subitem_title_language":"ja"},{"subitem_title":"Consideration and Proposal Concerning the Measurement of Fitness in Logistic Regression Analysis","subitem_title_language":"en"}]},"item_type_id":"1","owner":"3","path":["105"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2004-09-30"},"publish_date":"2004-09-30","publish_status":"0","recid":"320","relation_version_is_last":true,"title":["ロジスティック回帰分析におけるモデルの適合度指標に関する考察と提案"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-12-22T07:12:33.702060+00:00"}