検索結果:　 242件中 1-20 を表示

  • 1

    Improved transformed deviance statistic for testing a logistic regression model

    Taneichi Nobuhiro , Sekiya Yuri , Toyama Jun

    … In logistic regression models, we consider the deviance statistic (the log likelihood ratio statistic) D as a goodness-of-fit test statistic. …

    Journal of Multivariate Analysis 102(9), 1263-1279, 2011-10

    機関リポジトリ CrossRef

  • 2

    Isolated Coronary Artery Bypass Grafting in Obese Individuals : A Propensity Matched Analysis of Outcomes

    ALAM Mahboob , SIDDIQUI Sahar , LEE Vei-Vei , ELAYDA McArthur A. , NAMBI Vijay , YANG Eric Y. , JNEID Hani M. , WILSON James M. , BALLANTYNE Christie M. , VIRANI Salim S.

    … Propensity-matched stepwise multivariable logistic regression was performed. … In the propensity-matched logistic regression models (n=8,442), obesity was not associated with postoperative mortality (odds ratio=1.13, 95% confidence interval 0.86-1.48). …

    Circulation journal : official journal of the Japanese Circulation Society 75(6), 1378-1385, 2011-05-25

    J-STAGE 医中誌 CrossRef 参考文献64件

  • 3

    Language Recognition Based on Acoustic Diversified Phone Recognizers and Phonotactic Feature Fusion

    DENG Yan , ZHANG Wei-Qiang , QIAN Yan-Min , LIU Jia

    … For the model training, we examine the use of the maximum likelihood and feature minimum phone error methods to train complementary acoustic models. … A novel logistic regression optimized weighting (LROW) approach is introduced for fusion factor optimization. …

    IEICE transactions on information and systems 94(3), 679-689, 2011-03-01

    J-STAGE CrossRef 参考文献26件

  • 4

    在宅重度要介護高齢者の排泄介護における家族介護者の負担に関連する要因

    菊池 有紀 , 薬袋 淳子 , 島内 節

    在宅において家族介護者の90%が排泄介護を行っており,介護負担の大きな要因となっている。特に,重度要介護高齢者の排泄介護における負担は大きい。本研究は,在宅で重度要介護高齢者の排泄介護を行っている家族介護者の身体的,心理的,社会・経済的3側面の負担を高める要因を明らかにすることを目的とした。家族介護者に自記式質問紙調査を行い,150人について分析を行った。身体的負担がある家族介護者が71%で最も多 …

    国際医療福祉大学紀要 15(2), 13-23, 2011-01-31

    CiNii PDF - オープンアクセス  医中誌

  • 5

    複雑系,カオス,フラクタル,経済物理による経済分析 ANOVA type logistic regression models

    布能 英一郎

    … Logistic regression is the most important statistical model for categorical response data. … On the other hand, for two-dimensional contingency table where outcome of each cell is from the binomial random variable, Hirotsu (1982) considered the logistic parameter transformation for the binomial parameter, and proposed the ANOVA type modeling for this data. …

    関東学院大学経済経営研究所年報 33, 96-116, 2011-03

    機関リポジトリ

  • 6

    鉄道輸送による中国の省間物流動向

    坂本 博

    … Second, the study estimates the future distribution by stochastic models represented by the Markov chain. … If the trends in logistics do not change through time, it is difficult to suggest a logistic policy, especially in terms of railway transportation, to reduce regional disparity. … The policy for constructing a railway logistic center in poor regions to reduce disparity is not realistic. …

    地域学研究 41(2), 505-522, 2011

    J-STAGE CrossRef

  • 7

    Comparison of a Sleep Item From the General Health Questionnaire-12 With the Jenkins Sleep Questionnaire as Measures of Sleep Disturbance

    Lallukka Tea , Dregan Alexandru , Armstrong David

    … Using the above 2 measures of sleep, logistic regression models were used to examine associations between sociodemographic factors, working conditions, health-related factors, and sleep disturbance.Results: The estimated area under the ROC curve was 0.68 among both women and men, which suggests that the ability of the GHQ-12 item to discriminate true positives from false positives was modest. …

    Journal of Epidemiology 21(6), 474-480, 2011

    J-STAGE CrossRef

  • 8

    Twelve-year Cumulative Incidence of Airflow Obstruction among Japanese Males

    Omori Hisamitsu , Nagano Megumi , Funakoshi Yayoi , Onoue Ayumi , Mihara Shuichi , Marubayashi Tohru , Kohrogi Hirotsugu , Aizawa Hisamichi , Katoh Takahiko

    … In logistic regression models, the odds ratio (OR) of developing airflow obstruction defined using the fixed criteria and the LLN criteria increased with a history of smoking status and increasing pack-years of smoking. …

    Internal Medicine 50(15), 1537-1544, 2011

    J-STAGE CrossRef

  • 9

    Characteristics of Outpatients Initiated on Olanzapine versus Risperidone in the Treatment of Schizophrenia in Japan: A Healthcare Database Analysis

    Ye Wenyu , Nakahara Naohiro , Takahashi Michihiro , Ascher-Svanum Haya

    … Multivariate logistic regressions were used to assess the independent contribution of the predictors. … Results: In both the multivariate and univariate models, olanzapine-initiated patients (n=334) were more likely than risperidone-initiated patients (n=502) to have a history of treatment with antidepressants (56.6% vs. 43.8%, p < …

    Clinical Neuropsychopharmacology and Therapeutics 2(0), 1-8, 2011

    J-STAGE CrossRef

  • 10

    Smoking During Pregnancy Increases Risks of Various Obstetric Complications: A Case-Cohort Study of the Japan Perinatal Registry Network Database

    Hayashi Kunihiko , Matsuda Yoshio , Kawamichi Yayoi , Shiozaki Arihiro , Saito Shigeru

    … Logistic regression models were used to estimate age-adjusted risk ratios (aRRs) and relative excess incidence proportions (REIs).Results: The overall prevalence of smoking during pregnancy was 5.8% in the base cohort, and the prevalence was higher among younger women. …

    Journal of Epidemiology advpub(0), 1011100202, 2011

    J-STAGE CrossRef

  • 11

    A UML Approximation of Three Chidamber-Kemerer Metrics and Their Ability to Predict Faulty Code across Software Projects

    CAMARGO CRUZ Ana Erika , OCHIMIZU Koichiro

    … Finally, we construct three prediction models with the source code of a package of an open source software project (Mylyn from Eclipse), and we test them with several other packages and three different small size software projects, using their UML and code metrics for comparison. …

    IEICE transactions on information and systems 93(11), 3038-3050, 2010-11-01

    J-STAGE CrossRef 参考文献37件

  • 12

    Development and Application of a Forest Fire Danger Rating System in South Korea

    Won Myoung Soo , Lee Si Young , Lee Myung Bo , Ohga Shoji , 大賀 祥治

    … DWI represents the meteorological characteristics, such as effective humidity, temperature and wind speed, and is adapted to local conditions through the use of one of eight logistic regression models. …

    Journal of the Faculty of Agriculture, Kyushu University 55(2), 221-229, 2010-10-29

    機関リポジトリ

  • 13

    感染病拡大予測と最近の実例

    廣瀬 英雄 , 松隈 和広 , 河野 翼 , 作村 建紀

    疫病感染拡大予測モデルとして,微分方程式によるSIRモデルや,統計的なtruncatedモデルを採用し,SARS,新型インフルエンザ,口蹄疫(FMD)の事例に両モデルを適用し,SIRモデルとtruncatedモデルの結果を比較する.これにより,各モデルのパンデミックの早期および終息段階期での活用法を示唆する.また,SIRモデルでのパラメータ最適決定法(BBS法)についても触れる.早期には,SIRは …

    電子情報通信学会技術研究報告. R, 信頼性 110(262), 15-20, 2010-10-22

    CiNii PDF - 未公開  参考文献37件

  • 14

    Superfast-Trainable Multi-Class Probabilistic Classifier by Least-Squares Posterior Fitting

    SUGIYAMA Masashi

    … Kernel logistic regression (KLR) is a powerful and flexible classification algorithm, which possesses an ability to provide the confidence of class prediction. … KLR models the class-posterior probability by the log-linear combination of kernel functions and its parameters are learned by (regularized) maximum likelihood. …

    IEICE transactions on information and systems 93(10), 2690-2701, 2010-10-01

    J-STAGE CrossRef 参考文献36件 被引用文献5件

  • 15

    Development of a New Logistic Model for Microbial Growth in Foods

    FUJIKAWA HIROSHI

    … Mathematical models are essentially needed to quantitatively predict microbial growth in food products during their production and distribution. … Recently we developed a new logistic model for microbial growth. … The model is an extended logistic model, which shows a sigmoid curve on a semi-log plot. …

    Biocontrol science 15(3), 75-80, 2010-09-10

    J-STAGE 医中誌 CrossRef 参考文献12件 被引用文献1件

  • 16

    非線形判別分析とその周辺(コンピュータビジョンとパターン認識のための機械学習と最適化,一般)

    栗田 多喜夫

    判別分析は、識別のための良い特徴を抽出するための最も有名な手法のひとつである。大津は、判別分析の本質的な意味を理解するために、判別規準を最大とする究極の非線形判別写像を導出し、それがベイズ識別と密接に関係していることを示した。また、線形判別分析がベイズ事後確率の線形近似を通してこの究極の非線形判別分析を近似していることを明らかにした。これらの結果は、事後確率を推定する手法があれば、究極の非線形判別 …

    電子情報通信学会技術研究報告. PRMU, パターン認識・メディア理解 110(187), 209-214, 2010-08-29

    CiNii PDF - 未公開 

  • 17

    非線形判別分析とその周辺(コンピュータビジョンとパターン認識のための機械学習と最適化,一般)

    栗田 多喜夫

    判別分析は、識別のための良い特徴を抽出するための最も有名な手法のひとつである。大津は、判別分析の本質的な意味を理解するために、判別規準を最大とする究極の非線形判別写像を導出し、それがべイズ識別と密接に関係していることを示した。また、線形判別分析がべイズ事後確率の線形近似を通してこの究極の非線形判別分析を近似していることを明らかにした。これらの結果は、事後確率を推定する手法があれば、究極の非線形判別 …

    電子情報通信学会技術研究報告. IBISML, 情報論的学習理論と機械学習 110(188), 209-214, 2010-08-29

    CiNii PDF - 未公開  参考文献22件

  • 18

    我が国における鈍的外傷患者の生存予測ロジスティック回帰式の検討 第二報

    木村 昭夫

    日本外傷学会雑誌 = Journal of the Japanese Association for the Surgery of Trauma 24(3), 321-326, 2010-07-20

    参考文献14件

  • 19

    HLA-A Alleles and the Risk of Cervical Squamous Cell Carcinoma in Japanese Women

    HOSONO Satoyo , KAWASE Takakazu , MATSUO Keitaro , WATANABE Miki , KAJIYAMA Hiroaki , HIROSE Kaoru , SUZUKI Takeshi , KIDOKORO Kumiko , ITO Hidemi , NAKANISHI Toru , YATABE Yasushi , HAMAJIMA Nobuyuki , KIKKAWA Fumitaka , TAJIMA Kazuo , TANAKA Hideo

    … The estimated impact of HLA-A alleles on cervical cancer risk was evaluated by unconditional logistic regression models.Results: The frequency of HLA-A*0206 among cases was significantly lower than among controls (P = 0.006). …

    Journal of epidemiology 20(4), 295-301, 2010-07-01

    J-STAGE 医中誌 CrossRef 参考文献46件

  • 20

    入院日数の分布モデル

    高山 学

    入院リスクは一般に,入院発生率と平均在院日数の積で表されるが,平均在院日数は更に,μリスク(中央値)とσリスク(平均値÷中央値)との積に分解される。入院初日より入院給付金を支払った約7万件の保険契約を対象に,生存時間解析を行った結果,AIC(赤池情報量規準)で,対数ロジスティック分布が最適であった。そこで,対数ロジスティック分布モデルで,平均在院日数をμリスクとσリスクに分解し,性別・年齢階級別に …

    日本保険医学会誌 108(2), 120-134, 2010-06-17

    CiNii PDF - 有料  医中誌 参考文献32件