Advances in Differentially Methylated Region Detection and Cure Survival Models

<p>"This dissertation focuses on two areas of statistics: DNA methylation and survival analysis. The first part of the dissertation pertains to the detection of differentially methylated regions in the human genome. The varying distribution of gaps between succeeding genomic locations, which are represented on the microarray used to quantify methylation, makes it challenging to identify regions that have differential methylation. This emphasizes the need to properly account for the correlation in methylation shared by nearby locations within a specific genomic distance. In this work, a normalized kernel-weighted statistic is proposed to obtain an optimal amount of "information" from neighboring locations to detect those differences. The large sample properties of the proposed statistic are also studied. Simulation studies show that the proposed method captures the true length of differentially methylated regions more accurately than a widely used existing method.</p> <p>The second focus area of the dissertation pertains to mixture cure models in survival analysis. Mixture cure models are those based on a cured and uncured population. The choice of models for the cured and uncured is crucial in developing statistical models for this type of population. In this work, a flexible mixture cure model is proposed that incorporates a generalized partially linear single-index model for modeling the cure part and an additive hazard model for the uncured. This model proves to be particularly effective when dealing with large data sets where an underlying baseline mechanism is expected. In such cases, limited models like the logistic regression are not suitable. By employing the additive hazard model, the proposed approach offers an alternative for modeling cure survival data, especially when hazard differences are of interest and the proportional hazard assumption is violated"--Abstract, p. iv</p>

Name thesis:degree_name

Ph. D. in Mathematics and Statistics

Grantor

Missouri University of Science and Technology

Author dc:creator

• Alhassan, Daniel Ahmed

• Mathematics
• Physical Sciences and Mathematics
• Statistics and Probability

Repository record dc:identifier

https://scholarsmine.mst.edu/doctoral_dissertations/3269

OAI identifier oai:identifier

oai:scholarsmine.mst.edu:doctoral_dissertations-4274