Randomization Tests for Regression Models in Clinical Trials

Simple item page
dc.contributor.advisorRosenberger, William F.
dc.contributor.authorParhat, Parwen
dc.creatorParhat, Parwen
dc.date.accessioned2013-08-09T15:40:06Z
dc.date.available2013-08-09T15:40:06Z
dc.date.issued2013
dc.description.abstractIn this dissertation, we apply randomization tests in the context of regression models to detect treatment effects for clinical trial data. This application allows us to compute randomization tests for a wide variety of outcomes, including covariate adjusted treatment effects, general response functions, survival data, and longitudinal data. We used score residuals as the outcome of the randomization test under the generalized linear model. For the proportional hazards and accelerated linear model, we used the martingales residuals as the outcome of the randomization test. For the generalized linear mixed model, to detect whether there is a time-varying treatment effect, we compute the predicted random slope from the regression as the outcome of the randomization test.
dc.format.extent189 pages
dc.identifier.urihttps://hdl.handle.net/1920/8287
dc.language.isoen
dc.rightsCopyright 2013 Parwen Parhat
dc.subjectStatistics
dc.subjectClinical trials
dc.subjectMonte Carlo
dc.subjectRandomization test
dc.titleRandomization Tests for Regression Models in Clinical Trials
dc.typeDissertation
thesis.degree.disciplineStatistical Science
thesis.degree.grantorGeorge Mason University
thesis.degree.levelDoctoral

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Parhat_gmu_0883E_10363.pdf
Size:
743.92 KB
Format:
Adobe Portable Document Format
Download

Collections

College of Engineering and Computing