Regression analysis with clustered data.

Clustered data are found in many different types of studies, for example, studies involving repeated measures, inter-rater agreement studies, household surveys, crossover designs and community randomized trials. Analyses based on population average and cluster specific models are commonly used for estimating treatment (exposure) effects with clustered data. This paper discusses conditions when one or both types of models are appropriate for estimating causal effects and when there is agreement between population average and cluster specific analyses. Applications of survey sampling methods to the robust estimation of standard errors of estimated treatment parameters are discussed.

[1]  H. Smith.  Interpretation of Adjusted Treatment Means and Regressions in Analysis of Covariance , 1957 .

[2]  M. Rosenberg,et al.  The Logic of Survey Analysis. , 1968 .

[3]  Michail Prodan,et al.  CHAPTER 17 – THE PLANNING OF EXPERIMENTS , 1968 .

[4]  D. Rubin.  Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[5]  A S Whittemore,et al.  Methods for analyzing panel studies of acute health effects of air pollution. , 1979, Biometrics.

[6]  P. W. Lane,et al.  Analysis of covariance and standardization as instances of prediction. , 1982, Biometrics.

[7]  D. Binder.  On the variances of asymptotically normal estimators from complex surveys , 1983 .

[8]  J. Ware,et al.  Random-effects models for serial observations with binary response. , 1984, Biometrics.

[9]  M. Gail,et al.  Biased estimates of treatment effect in randomized experiments with nonlinear regressions and omitted covariates , 1984 .

[10]  P. Rosenbaum.  The Consequences of Adjustment for a Concomitant Variable that Has Been Affected by the Treatment , 1984 .

[11]  K. Wolter.  Introduction to Variance Estimation , 1985 .

[12]  J R Landis,et al.  Blood lead and blood pressure. Relationship in the adolescent and adult US population. , 1985, JAMA.

[13]  R. Royall.  Model robust confidence intervals using maximum likelihood estimators , 1986 .

[14]  P. Holland.  Statistics and Causal Inference , 1985 .

[15]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[16]  R. Jennrich,et al.  Unbalanced repeated-measures models with structured covariance matrices. , 1986, Biometrics.

[17]  S. Snapinn,et al.  Tests of significance using regression models for ordered categorical data. , 1986, Biometrics.

[18]  K Y Liang,et al.  Longitudinal data analysis for discrete and continuous outcomes. , 1986, Biometrics.

[19]  E. Korn,et al.  Examining neighbourhood confounding in a survey: an example using the National Health and Nutrition Examination Survey II. , 1988, Statistics in medicine.

[20]  M. Gail.  The Effect of Pooling Across Strata in Perfectly Balanced Studies , 1988 .

[21]  L. Ryan,et al.  The Analysis of Multiple Correlated Binary Outcomes: Application to Rodent Teratology Experiments , 1989 .

[22]  Christine Waternaux,et al.  Methods for Analysis of Longitudinal Data: Blood-Lead Concentrations and Cognitive Development , 1989 .

[23]  G G Koch,et al.  An overview of statistical issues and methods of meta-analysis. , 1991, Journal of biopharmaceutical statistics.

[24]  J M Neuhaus,et al.  An annotated bibliography of methods for analysing correlated categorical data. , 1992, Statistics in medicine.

[25]  David A. Binder,et al.  Fitting Cox's proportional hazards models from survey data , 1992 .

[26]  J M Neuhaus,et al.  Statistical methods for longitudinal and clustered designs with binary responses , 1992, Statistical methods in medical research.

[27]  M. Kenward,et al.  Alternative approaches to the analysis of binary and categorical repeated measurements. , 1992, Journal of biopharmaceutical statistics.