Will Chen

Document Type

Honors Thesis


Motivated from lung cancer study data, we consider a model �� = �� + ��, where �� is an observable variable and �� is a hidden variable contaminated in �� with a measurement error ��. Such a model can also apply to studies in microfluorimetry, electrophoresis, biostatistics, and some other fields, where the measurements �� cannot be observed directly. The objective of this project is to estimate the hazard rate of the unobservable survival time �� in a lung cancer study. Assuming the additive measurement error �� has a known distribution, we combine deconvolution kernel density estimation and inverse-probability- of-censoring weighting methods to formulate a nonparametric hazard rate estimator based on random right-censored observations of ��, when the distribution of �� is unknown. Simulation studies show that the estimator performs well when sample sizes are relatively large.

Publication Date






To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.