An investigation on measures of explained variation in survival analysis

被引:14
作者
Graf, E [1 ]
Schumacher, M [1 ]
机构
[1] UNIV FREIBURG, INST MED BIOMETRY & MED INFORMAT, D-79104 FREIBURG, GERMANY
关键词
binary data; coefficient of determination; explained variation; residual variation; survival analysis;
D O I
10.2307/2348898
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Two measures of explained variation for survival data have been proposed by Korn and Simon and by Schemper. In this paper, we demonstrate how these measures compare and work out the conceptual differences between them. Both compare the variance when a covariate is accounted for with the variance when it is ignored, but only the second incorporates differences between observed and fitted outcomes. First, the relationship between both measures is studied for the situation without censoring. It turns out that considering the explained variation as a process in time is helpful in this context as well as in its own right. Censoring is incorporated quite differently for the two measures. We illustrate the points made by examples of fictitious data and a study on the treatment of breast cancer.
引用
收藏
页码:497 / 507
页数:11
相关论文
共 21 条
[1]  
Andersen P, 1993, STATISTICAL MODELS B
[2]   HISTOLOGICAL GRADING AND PROGNOSIS IN BREAST CANCER - A STUDY OF 1409 CASES OF WHICH 359 HAVE BEEN FOLLOWED FOR 15 YEARS [J].
BLOOM, HJG ;
RICHARDSON, WW .
BRITISH JOURNAL OF CANCER, 1957, 11 (03) :359-&
[3]   A COMMENT ON THE COEFFICIENT OF DETERMINATION FOR BINARY RESPONSES [J].
COX, DR ;
WERMUTH, N .
AMERICAN STATISTICIAN, 1992, 46 (01) :1-4
[4]  
COX DR, 1972, J R STAT SOC B, V34, P187
[7]  
ELHASNAOUI A, 1992, METHOD INFORM MED, V31, P275
[8]  
Harrel F, 1986, SUGI SUPPLEMENTAL LI, P437
[9]   MEASURES OF DEPENDENCE FOR CENSORED SURVIVAL-DATA [J].
KENT, JT ;
OQUIGLEY, J .
BIOMETRIKA, 1988, 75 (03) :525-534
[10]   MEASURES OF EXPLAINED VARIATION FOR SURVIVAL-DATA [J].
KORN, EL ;
SIMON, R .
STATISTICS IN MEDICINE, 1990, 9 (05) :487-503