A review of multilevel theory for ecologic analyses

被引:64
作者
Greenland, S
机构
[1] Univ Calif Los Angeles, Coll Letters & Sci, Dept Stat, Los Angeles, CA 90095 USA
[2] Univ Calif Los Angeles, Sch Publ Hlth, Dept Epidemiol, Los Angeles, CA 90095 USA
关键词
ecologic analysis; multilevel theory;
D O I
10.1002/sim.1024
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
This paper reviews multilevel and conventional models for the analysis of ecologic (group, aggregate) data. It emphasizes the non-separability of contextual (group-level) effects and individual-level effects that arises from the multilevel structure of the underlying effects. Contrary to common misperceptions, this problem afflicts ecologic studies in which the sole objective is to estimate contextual effects, as well as studies in which the objective is to estimate individual effects. Multilevel effects also severely complicate causal interpretations of model coefficients. Copyright (C) 2002 John Wiley Sons, Ltd.
引用
收藏
页码:389 / 395
页数:7
相关论文
共 25 条
[1]  
Achen ChristopherH., 1995, CROSS LEVEL INFERENC
[2]  
[Anonymous], MODERN EPIDEMIOLOGY
[3]  
[Anonymous], 1981, QUANT GEOGR BR VIEW, DOI DOI 10.1002/9781118526729.CH3
[4]  
[Anonymous], 1991, CONTEXTUAL ANAL
[5]  
[Anonymous], 2000, CAUSALITY
[6]   PROPORTIONAL HAZARDS MODELS FOR AVERAGE DATA FOR GROUPS [J].
DOBSON, AJ .
STATISTICS IN MEDICINE, 1988, 7 (05) :613-618
[7]  
FIREBAUGH G, 1978, AM SOCIOL REV, V43, P557, DOI 10.2307/2094779
[8]  
FIREBAUGH G, 1980, AGGREGATE DATA ANAL, P13
[9]  
GOLDSTEIN H, 1995, MULTILEVEL MODELS
[10]  
Greenland S, 1999, SCAND J WORK ENV HEA, V25, P43