Likelihood Methods for Treatment Noncompliance and Subsequent Nonresponse in Randomized Trials
- 1 June 2005
- journal article
- clinical trial
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 61 (2) , 325-334
- https://doi.org/10.1111/j.1541-0420.2005.040313.x
Abstract
SummaryWhile several new methods that account for noncompliance or missing data in randomized trials have been proposed, the dual effects of noncompliance and nonresponse are rarely dealt with simultaneously. We construct a maximum likelihood estimator (MLE) of the causal effect of treatment assignment for a two‐armed randomized trial assuming all‐or‐none treatment noncompliance and allowing for subsequent nonresponse. The EM algorithm is used for parameter estimation. Our likelihood procedure relies on a latent compliance state covariate that describes the behavior of a subject under all possible treatment assignments and characterizes the missing data mechanism as inFrangakis and Rubin(1999,Biometrika86,365–379). Using simulated data, we show that the MLE for normal outcomes compares favorably to the method‐of‐moments (MOM) and the standard intention‐to‐treat (ITT) estimators under (1) both normal and nonnormal data, and (2) departures from the latent ignorability and compound exclusion restriction assumptions. We illustrate methods using data from a trial to compare the efficacy of two antipsychotics for adults with refractory schizophrenia.Keywords
This publication has 16 references indexed in Scilit:
- Covariate adjustment in clinical trials with non‐ignorable missing data and non‐complianceStatistics in Medicine, 2004
- Principal Stratification Approach to Broken Randomized ExperimentsJournal of the American Statistical Association, 2003
- Statistical power in randomized intervention studies with noncompliance.Psychological Methods, 2002
- Molecular diversity of arbuscular mycorrhizal fungi colonising arable cropsFEMS Microbiology Ecology, 2001
- Assessing the effect of an influenza vaccine in an encouragement designBiostatistics, 2000
- Estimation of the Causal Effect of a Time-Varying Exposure on the Marginal Mean of a Repeated Binary OutcomeJournal of the American Statistical Association, 1999
- Addressing complications of intention-to-treat analysis in the combined presence of all-or-none treatment-noncompliance and subsequent missing outcomesBiometrika, 1999
- A Comparison of Clozapine and Haloperidol in Hospitalized Patients with Refractory SchizophreniaNew England Journal of Medicine, 1997
- Bayesian inference for causal effects in randomized experiments with noncomplianceThe Annals of Statistics, 1997
- Statistics and Causal InferenceJournal of the American Statistical Association, 1986