Doctoral Dissertations

Recurrent Event Data Analysis with Mismeasured Covariates

Ravinath Alahakoon Mudiyanselage, Missouri University of Science and Technology


Consider a study with n units wherein every unit is monitored for the occurrence of an event that can recur with random end of monitoring. At each recurrence, p concomitant variables associated to the event recurrence are recorded with q (q<=p) collected with errors. Of interest in this dissertation is the estimation of the regression parameters of event time regression models accounting for the covariates. To circumvent the problem of bias and consistency associated with model's parameter estimation in the presence of measurement errors, we propose inference for corrected estimating functions with well-behaved roots under additive measurement errors model. We consider two types of failure time regression models: one with additive effects and the other with multiplicative effects on the pure event history. We show that estimation is essentially unbiased under the corrected profile likelihood for recurrent events, in comparison to biased estimations under a likelihood function that ignores correction in both cases. We propose methods for obtaining estimators of error variance and discuss the property of the estimators. We further investigate the case of misspecified error models under the multiplicative regression model and show that the resulting estimators under misspecification converge to a value different from that of the true parameter--thereby providing a basis for bias assessment. In both cases, simulation studies indicate that the asymptotic properties of the regression parameters closely approximate its finite sample properties. We demonstrate the foregoing correction methods on an open source rhDNase dataset which was gathered in a clinical setting.