Model misspecification sensitivity analysis in estimating causal effects of interventions with non‐compliance

Randomized trials often face complications in assessing the effect of treatment because of study participants' non-compliance. If compliance type is observed in both the treatment and control conditions, the causal effect of treatment can be estimated for a targeted subpopulation of interest based on compliance type. However, in practice, compliance type is not observed completely. Given this missing compliance information, the complier average causal effect (CACE) estimation approach provides a way to estimate differential effects of treatments by imposing the exclusion restriction for non-compliers. Under the exclusion restriction, the CACE approach estimates the effect of treatment assignment for compliers, but disallows the effect of treatment assignment for non-compliers. The exclusion restriction plays a key role in separating outcome distributions based on compliance type. However, the CACE estimate can be substantially biased if the assumption is violated. This study examines the bias mechanism in the estimation of CACE when the assumption of the exclusion restriction is violated. How covariate information affects the sensitivity of the CACE estimate to violation of the exclusion restriction assumption is also examined.

[1]  J. Angrist,et al.  Identification and Estimation of Local Average Treatment Effects , 1994 .

[2]  M. A. Tanner,et al.  Tools for Statistical Inference: Methods for the Exploration of Posterior Distributions and Likelihood Functions, 3rd Edition , 1998 .

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

[4]  D. Rubin,et al.  Statistical Analysis with Missing Data , 1988 .

[5]  Booil Jo,et al.  Statistical power in randomized intervention studies with noncompliance. , 2002 .

[6]  A. Vinokur,et al.  Impact of the JOBS intervention on unemployed workers varying in risk for depression , 1995, American journal of community psychology.

[7]  Howard S. Bloom,et al.  Accounting for No-Shows in Experimental Evaluation Designs , 1984 .

[8]  Booil Jo,et al.  Estimation of Intervention Effects with Noncompliance: Alternative Model Specifications , 2002 .

[9]  D. Rubin.  Randomization Analysis of Experimental Data: The Fisher Randomization Test Comment , 1980 .

[10]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[11]  A. Vinokur,et al.  From field experiments to program implementation: Assessing the potential outcomes of an experimental intervention program for unemployed persons , 1991, American journal of community psychology.

[12]  R. Little,et al.  Statistical Techniques for Analyzing Data from Prevention Trials: Treatment of No-Shows Using Rubin's Causal Model , 1998 .

[13]  A. Vinokur,et al.  Mastery and inoculation against setbacks as active ingredients in the JOBS intervention for the unemployed. , 1997, Journal of consulting and clinical psychology.

[14]  Julian Barling,et al.  Employment, Stress, And Family Functioning , 1990 .

[15]  Geert Molenberghs,et al.  Causal Inference in a Placebo-Controlled Clinical Trial with Binary Outcome and Ordered Compliance , 1996 .

[16]  A. Vinokur,et al.  Impact of a preventive job search intervention on the likelihood of depression among the unemployed. , 1992, Journal of health and social behavior.

[17]  L. Covi,et al.  The Hopkins Symptom Checklist (HSCL). A measure of primary symptom dimensions. , 1974, Modern problems of pharmacopsychiatry.

[18]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[19]  D. Rubin,et al.  Statistical Analysis with Missing Data. , 1989 .

[20]  D. Rubin,et al.  Identification of Causal Effects Using Instrumental Variables: Rejoinder , 1996 .

[21]  D. Rubin,et al.  Assessing the effect of an influenza vaccine in an encouragement design. , 2000, Biostatistics.

[22]  Booil Jo,et al.  Statistical power in randomized intervention studies with noncompliance. , 2002, Psychological methods.

[23]  Guido W. Imbens,et al.  Average Causal Response with Variable Treatment Intensity , 1995 .

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

[25]  L. Covi,et al.  The Hopkins Symptom Checklist (HSCL)--factors derived from the HSCL-90. , 1979, Journal of affective disorders.

[26]  D. Rubin,et al.  Intention‐to‐treat analysis and the goals of clinical trials , 1995, Clinical pharmacology and therapeutics.

[27]  D. Rubin,et al.  Bayesian inference for causal effects in randomized experiments with noncompliance , 1997 .

[28]  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 .

[29]  C. Glymour,et al.  STATISTICS AND CAUSAL INFERENCE , 1985 .