順序カテゴリカル応答に対する多変量適応型回帰スプライン法  [in Japanese] MULTIVARIATE ADAPTIVE REGRESSION SPLINE METHOD AND ITS APPLICATIONS  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

医学研究・社会科学などの実質科学分野では, データが順序尺度で得られることが少なくない. 本論文では, 順序カテゴリカル応答に対する影響要因を探索する方法として, 多変量適応型回帰スプライン (MARS: Multivariate Adaptive Regression Splines, Friedman, 1991) 法を順序カテゴリカル応答に拡張した. そこでは, 比例オッズ・モデルの説明変数の線形結合に代わりに, 打ち切りベキ乗基底関数を導入した. さらに, グラフィカル診断の方法として, 変数重要度および部分従属度を紹介した. 順序カテゴリカル応答に対するMARS法の有用性を文献事例により提示し, 予測確度を数値検証により評価した. その結果, 順序カテゴリカル応答に対するMARS法は比例オッズ・モデルおよび順序カテゴリカル応答に対するCART法に比べて予測確度に優れていた.

In medical research, ordered categorical outcomes (such as seriousness, side effects, and grade of treatment) are sometimes used as response variables. Typically, the influencing factors are explored by ordered logistic regression. Recently, the tree-structured method has been extended to ordered categorical outcomes (Piccarreta, 2008; Archer, 2010), but the predictive outcomes of this approach are poor. In this paper, we newly develop a nonlinear ordered categorical regression method, named PO-MARS, which extends multivariate adaptive regression splines (Friedman, 1991). The PO-MARS method is developed on a proportional odds model framework, and model selection is based on the modified Akaike's information criteria (AIC) proposed by LeBlanc and Crowley (1999). The effectiveness of the PO-MARS method was illustrated through a practical example. In small-scale simulations, this method demonstrated higher predictive performance than existing methods.

Journal

  • Bulletin of the Computational Statistics of Japan

    Bulletin of the Computational Statistics of Japan 28(2), 121-136, 2015

    Japanese Society of Computational Statistics

Codes

  • NII Article ID (NAID)
    130005631736
  • NII NACSIS-CAT ID (NCID)
    AN10195854
  • Text Lang
    JPN
  • ISSN
    0914-8930
  • NDL Article ID
    027073711
  • NDL Call No.
    Z14-1382
  • Data Source
    NDL  J-STAGE 
Page Top