Coste J, Walter E, Wasserman D, Venot A
Département de Biostatistique et d'Informatique Médicale (Faculté Cochin-Université Paris V), Hôpital COCHIN, Paris, France.
Stat Med. 1997 Mar 15;16(5):561-9. doi: 10.1002/(sici)1097-0258(19970315)16:5<561::aid-sim431>3.0.co;2-c.
Optimal classification formulation is adapted to the context of discrimination when the response is ordinal. The resulting method, optimal discriminant analysis for ordinal responses (ODAO), is presented and compared with two reference discrimination techniques used in this context (proportional-odds ordinal logistic regression and normal discrimination) using a study of prognosis following burn injuries and simulated data. The ODAO method clearly outperforms both reference methods in terms of classification accuracy (in training and validation samples), robustness to outliers, simplicity of use and applicability in clinical settings. ODAO is a promising method for improving classification performance in discrimination with ordinal responses and merits further investigation.
当响应为有序变量时，最优分类公式适用于判别分析的情境。本文提出了由此产生的方法——有序响应最优判别分析（ODAO），并通过一项烧伤预后研究和模拟数据，将其与该情境下使用的两种参考判别技术（比例优势有序逻辑回归和正态判别）进行比较。在分类准确性（训练样本和验证样本中）、对异常值的稳健性、使用的简便性以及在临床环境中的适用性方面，ODAO方法明显优于这两种参考方法。ODAO是一种很有前景的方法，可用于提高有序响应判别分析中的分类性能，值得进一步研究。
