EFFECT OF REGRESSION TO MEAN IN EPIDEMIOLOGIC AND CLINICAL STUDIES

被引：339

作者：

DAVIS, CE ^{[1
]}

机构：

[1] UNIV N CAROLINA, DEPT BIOSTATISTICS, CHAPEL HILL, NC 27514 USA

来源：

AMERICAN JOURNAL OF EPIDEMIOLOGY | 1976年 / 104卷 / 05期

关键词：

D O I：

10.1093/oxfordjournals.aje.a112321

中图分类号：

R1 [预防医学、卫生学];

学科分类号：

1004 ; 120402 ;

摘要：

The ways in which regression to the mean can affect the measurement of treatment effects in clinical and epidemiologic studies are noted. Regression can have a sizeable effect and may lead to erroneous conclusions concerning treatment effects. The procedures outlined here should be useful in taking regression into account at the planning stage and at the time of analysis.

引用

页码：493 / 498

页数：6

共 7 条

[1] SERUM-CHOLESTEROL CHANGES - EFFECTS OF DIET AND REGRESSION TOWARD MEAN [J].

EDERER, F .

JOURNAL OF CHRONIC DISEASES, 1972, 25 (05) :277-&

[2] SOME EFFECTS OF WITHIN-PERSON VARIABILITY IN EPIDEMIOLOGICAL-STUDIES [J].

GARDNER, MJ ;

HEADY, JA .

JOURNAL OF CHRONIC DISEASES, 1973, 26 (12) :781-795

[3] REGRESSION TOWARD MEAN IN UNCONTROLLED CLINICAL STUDIES [J].

JAMES, KE .

BIOMETRICS, 1973, 29 (01) :121-130

[4]

*LIP RES CLIN, 1973, PROT LIP RES CLIN TY

[5]

*LIP RES CLIN, 1972, REF MAN LIP RES CLIN

[6]

REMINGTON RD, 1973, COLLOQUE INSERM, V21, P185

[7]

TALLIS GM, 1961, J ROY STAT SOC B, V23, P223

← 1 →