Monotone missing data and pattern-mixture models

被引：86

作者：

Molenberghs, G

Michiels, B

Kenward, MG

Diggle, PJ

机构：

[1] Limburgs Univ Ctr, B-3590 Diepenbeek, Belgium

[2] Univ Kent, Inst Math & Stat, Canterbury CT2 7NF, Kent, England

[3] Univ Lancaster, Dept Math & Stat, Lancaster LA1 4YF, England

来源：

STATISTICA NEERLANDICA | 1998年 / 52卷 / 02期

关键词：

missing at random; selection model;

D O I：

10.1111/1467-9574.00075

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：

It is shown that the classical taxonomy of missing data models, namely missing completely at random, missing at random and informative missingness, which has been developed almost exclusively within a selection modelling framework, can also be applied to pattern-mixture models. In particular, intuitively appealing identifying restrictions are proposed for a pattern-mixture MAR mechanism.

引用

页码：153 / 161

页数：9

共 8 条

[1]

Diggle P. G., 1994, J ROY STAT SOC C, V43, P49

[2]

Glynn RJ., 1986, Drawing Inferences from Self-Selected Samples, P115, DOI DOI 10.1007/978-1-4612-4976-4_10

[3]

LITTLE RJA, 1994, BIOMETRIKA, V81, P471

[4] PATTERN-MIXTURE MODELS FOR MULTIVARIATE INCOMPLETE DATA [J].