Estimating the causal effect of zidovudine on CD4 count with a marginal structural model for repeated measures

Even in the absence of unmeasured confounding factors or model misspecification, standard methods for estimating the causal effect of a time‐varying treatment on the mean of a repeated measures outcome (for example, GEE regression) may be biased when there are time‐dependent variables that are simultaneously confounders of the effect of interest and are predicted by previous treatment. In contrast, the recently developed marginal structural models (MSMs) can provide consistent estimates of causal effects when unmeasured confounding and model misspecification are absent. We describe an MSM for repeated measures that parameterizes the marginal means of counterfactual outcomes corresponding to prespecified treatment regimes. The parameters of MSMs are estimated using a new class of estimators – inverse‐probability of treatment weighted estimators. We used an MSM to estimate the effect of zidovudine therapy on mean CD4 count among HIV‐infected men in the Multicenter AIDS Cohort Study. We estimated a potential expected increase of 5.4 (95 per cent confidence interval ‐1.8,12.7) CD4 lymphocytes/l per additional study visit while on zidovudine therapy. We also explain the theory and implementation of MSMs for repeated measures data and draw upon a simple example to illustrate the basic ideas. Copyright © 2002 John Wiley & Sons, Ltd.

[1]  D. Horvitz,et al.  A Generalization of Sampling Without Replacement from a Finite Universe , 1952 .

[2]  Donald B. Rubin,et al.  Bayesian Inference for Causal Effects: The Role of Randomization , 1978 .

[3]  D. Pierce.  The Asymptotic Effect of Substituting Estimators for Parameters in Certain Types of Statistics , 1982 .

[4]  J. Robins.  A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect , 1986 .

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

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

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

[8]  J. Phair,et al.  The Multicenter AIDS Cohort Study: rationale, organization, and selected characteristics of the participants. , 1987, American journal of epidemiology.

[9]  J. Robins.  Addendum to “a new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect” , 1987 .

[10]  P. Rosenbaum.  Model-Based Direct Adjustment , 1987 .

[11]  J F Lawless,et al.  Likelihood analysis of multi-state models for disease incidence and mortality. , 1988, Statistics in medicine.

[12]  Douglas D. Richman,et al.  The safety and efficacy of zidovudine (AZT) in the treatment of subjects with mildly symptomatic human immunodeficiency virus type 1 (HIV) infection a double-blind, placebo-controlled trial , 1990 .

[13]  T. Speed,et al.  On the Application of Probability Theory to Agricultural Experiments. Essay on Principles. Section 9 , 1990 .

[14]  S W Lagakos,et al.  Zidovudine in Asymptomatic Human Immunodeficiency Virus Infection , 1990 .

[15]  D. Rubin.  [On the Application of Probability Theory to Agricultural Experiments. Essay on Principles. Section 9.] Comment: Neyman (1923) and Causal Inference in Experiments and Observational Studies , 1990 .

[16]  T. Merigan,et al.  Placebo-controlled trial to evaluate zidovudine in treatment of human immunodeficiency virus infection in asymptomatic patients with hemophilia. NHF-ACTG 036 Study Group. , 1991, Blood.

[17]  S Greenland,et al.  Analytic methods for two-stage case-control studies and other stratified designs. , 1991, Statistics in medicine.

[18]  J. Robins,et al.  Recovery of Information and Adjustment for Dependent Censoring Using Surrogate Markers , 1992 .

[19]  S L Zeger,et al.  The effects on survival of early treatment of human immunodeficiency virus infection. , 1992, The New England journal of medicine.

[20]  J. Currier.  Zidovudine for asymptomatic human immunodeficiency virus infection , 1994, ACP Journal Club.

[21]  J. Robins,et al.  Estimation of Regression Coefficients When Some Regressors are not Always Observed , 1994 .

[22]  D. Hawkins,et al.  A controlled trial of zidovudine in primary human immunodeficiency virus infection. , 1995, The New England journal of medicine.

[23]  James M. Robins,et al.  Causal Inference from Complex Longitudinal Data , 1997 .

[24]  Maia Berkane.  Latent Variable Modeling and Applications to Causality , 1997 .

[25]  J M Robins,et al.  Correction for non-compliance in equivalence trials. , 1998, Statistics in medicine.

[26]  James M. Robins,et al.  Causal Inference Without Counterfactuals: Comment , 2000 .

[27]  J. Robins,et al.  Sensitivity Analysis for Selection bias and unmeasured Confounding in missing Data and Causal inference models , 2000 .

[28]  James M. Robins,et al.  Marginal Structural Models versus Structural nested Models as Tools for Causal inference , 2000 .