CAUSALITY - SOME STATISTICAL ASPECTS

被引：128

作者：

COX, DR

机构：

来源：

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY | 1992年 / 155卷

关键词：

EPIDEMIOLOGY; ERROR OF MEASUREMENT; EXPERIMENT; INTERACTION; INTERVENTION; LATENT VARIABLE; OBSERVATIONAL STUDY; REGRESSION;

D O I：

10.2307/2982962

中图分类号：

O1 [数学]; C [社会科学总论];

学科分类号：

03 ; 0303 ; 0701 ; 070101 ;

摘要：

After some brief historical comments on statistical aspects of causality two current views are outlined and their limitations sketched. One definition is that causality is a statistical association that cannot be explained away by confounding variables and the other is based on a link with notions in the design of experiments. The importance of underlying processes or mechanisms is stressed. Implications for empirical statistical analysis are discussed.

引用

页码：291 / 301

页数：11

共 28 条

[1]

[Anonymous], 1982, ENCY STAT SCI

[2] MEASUREMENT ERROR IN THE GENERALIZED LINEAR-MODEL [J].

ARMSTRONG, B .

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 1985, 14 (03) :529-544

[3]

Cochran W., 1972, STATISTICAL PAPERS H, P77

[4] THE PLANNING OF OBSERVATIONAL STUDIES OF HUMAN-POPULATIONS [J].

COCHRAN, WG .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-GENERAL, 1965, 128 (02) :234-266

[5] RANDOMIZATION MODELS FOR MATCHED AND UNMATCHED 2 BY 2 TABLES [J].

COPAS, JB .

BIOMETRIKA, 1973, 60 (03) :467-476

[6]

Cox D.R., 1989, ANAL BINARY DATA

[7]

EFRON B, 1991, J AM STAT ASSOC, V86, P9, DOI 10.2307/2289707

[8]

GORE SM, 1984, APPL STAT-J ROY ST C, V33, P176

[9] ENVIRONMENT AND DISEASE - ASSOCIATION OR CAUSATION [J].

HILL, AB .

PROCEEDINGS OF THE ROYAL SOCIETY OF MEDICINE-LONDON, 1965, 58 (05) :295-+

[10]

HILL AB, 1937, PRINCIPLES MED STATI

← 1 2 3 →