Colloquium: Mission Imputable: Correcting for Berkson Error When Imputing a Censored Covariate

Dr. Tanya Garcia, University Of North Carolina-Chapel Hill, will give our department seminar Thursday, February 23 at 11:00 AM in 302 Divinity & Religious Studies Building.

Abstract: To select outcomes for clinical trials testing experimental therapies for Huntington disease, a fatal neurodegenerative disorder, analysts often model how possible outcomes change over time. Yet, subjects with Huntington disease are often observed at different levels of disease progression. To account for these differences, analysts include time to clinical diagnosis as a covariate in these models, but this covariate is often censored. With many solutions to covariate censoring, we impute censored values using predictions from a model of the censored covariate given other data, then analyze the imputed dataset. However, when this imputation model is misspecified, our outcome model estimates can be biased. To address this problem, we developed a novel method, dubbed “ACE imputation.” First, we model imputed times of diagnosis as error-prone versions of the true times of diagnosis. Then, we correct for these errors using semiparametric theory. Specifically, we derive an estimator of the outcome model that is consistent, even when the censored covariate is imputed using a misspecified imputation model. Simulation results show that ACE imputation remains empirically unbiased even if the imputation model is misspecified, unlike uncorrected imputation which yields >100% bias. Applying our method to a study of Huntington disease pinpoints outcomes for clinical trials aimed at slowing disease progression.