Bivariate density estimation with an application to survival analysis

被引：10

作者：

Kooperberg, C ^{[1
]}

机构：

[1] Fred Hutchinson Canc Res Ctr, Div Publ Hlth Sci, Seattle, WA 98109 USA

来源：

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS | 1998年 / 7卷 / 03期

关键词：

censoring; correlated data; splines; test of independence;

D O I：

10.2307/1390707

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：

A procedure for estimating a bivariate density based on data that may be censored is described. After the data are transformed to the unit square, the bivariate density is estimated using linear splines and their tensor products. The combined procedure yields an estimate of the bivariate density on the original scale, which may provide insight about the dependence structure. The procedure can also be used to estimate densities that are known to be symmetric and to test for independence.

引用

页码：322 / 341

页数：20

共 25 条

[1]

Andersen P. K., 2012, Statistical models based on counting processes

[2]

[Anonymous], 1992, MULTIVARIATE DENSITY

[3]

[Anonymous], 1964, Handbook of mathematical functions

[4]

CLAYTON DG, 1978, BIOMETRIKA, V65, P141, DOI 10.1093/biomet/65.1.141

[5]

Commenges D, 1995, Lifetime Data Anal, V1, P145, DOI 10.1007/BF00985764

[6] KAPLAN-MEIER ESTIMATE ON THE PLANE [J].

DABROWSKA, DM .

ANNALS OF STATISTICS, 1988, 16 (04) :1475-1489

[7]

DABROWSKA DM, 1995, UNPUB GRAPHICAL COMP

[8]

DUFFY DL, 1990, AM J HUM GENET, V47, P590

[9]

Gill P., 1986, 862 SOL STANF U DEP

[10]

GILL PE, 1986, 861 SOL STANF U DEP

← 1 2 3 →