Multilevel Modelling of Country Effects: A Cautionary Tale

被引：527

作者：

Bryan, Mark L. ^{[1
]}

Jenkins, Stephen P. ^{[1
,2
,3
]}

机构：

[1] Univ Essex, Inst Social & Econ Res, Colchester CO4 3SQ, Essex, England

[2] London Sch Econ, Dept Social Policy, London WC2A 2AE, England

[3] IZA, D-53113 Bonn, Germany

来源：

EUROPEAN SOCIOLOGICAL REVIEW | 2016年 / 32卷 / 01期

基金：

英国经济与社会研究理事会;

关键词：

SAMPLE-SIZE; SIMULATION; INFERENCE; ISSUES; PERFORMANCE; ESTIMATORS; PRECISION;

D O I：

10.1093/esr/jcv059

中图分类号：

C91 [社会学];

学科分类号：

030301 ; 1204 ;

摘要：

Country effects on outcomes for individuals are often analysed using multilevel (hierarchical) models applied to harmonized multi-country data sets such as ESS, EU-SILC, EVS, ISSP, and SHARE. We point out problems with the assessment of country effects that appear not to be widely appreciated, and develop our arguments using Monte Carlo simulation analysis of multilevel linear and logit models. With large sample sizes of individuals within each country but only a small number of countries, analysts can reliably estimate individual-level effects but estimates of parameters summarizing country effects are likely to be unreliable. Multilevel modelling methods are no panacea.

引用

页码：3 / 22

页数：20

共 48 条

[1]

Angrist JD, 2009, MOSTLY HARMLESS ECONOMETRICS: AN EMPIRICISTS COMPANION, P1

[2]

[Anonymous], 2014, Bayesian methods: A social and behavioral sciences approach

[3]

[Anonymous], 2013, Bayesian data analysis, third edition

[4]

[Anonymous], 2012, STAT STAT SOFTW REL

[5]

[Anonymous], 2010, MICROECONOMETRICS US

[6]

[Anonymous], 2002, HIERARCHICAL LINEAR

[7] Estimating Multilevel Logistic Regression Models When the Number of Clusters is Low: A Comparison of Different Statistical Software Procedures [J].

Austin, Peter C. .

INTERNATIONAL JOURNAL OF BIOSTATISTICS, 2010, 6 (01)

[8] How Low Can You Go? An Investigation of the Influence of Sample Size and Model Complexity on Point and Interval Estimates in Two-Level Linear Models [J].

Bell, Bethany A. ;

Morgan, Grant B. ;

Schoeneberger, Jason A. ;

Kromrey, Jeffrey D. ;

Ferron, John M. .

METHODOLOGY-EUROPEAN JOURNAL OF RESEARCH METHODS FOR THE BEHAVIORAL AND SOCIAL SCIENCES, 2014, 10 (01) :1-11

[9] A 2-STAGE ESTIMATOR FOR PROBIT MODELS WITH STRUCTURAL GROUP EFFECTS [J].

BORJAS, GJ ;

SUEYOSHI, GT .

JOURNAL OF ECONOMETRICS, 1994, 64 (1-2) :165-182

[10] EDA for HLM: Visualization when probabilistic inference fails [J].

Bowers, J ;

Drake, KW .

POLITICAL ANALYSIS, 2005, 13 (04) :301-326

← 1 2 3 4 5 →