Online Program Home
My Program

Abstract Details

Activity Number: 126
Type: Contributed
Date/Time: Monday, August 1, 2016 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract #319818 View Presentation
Title: Modeling Micronuclei Count Data Using the Generalized Monotone Incremental Forward Stagewise Method: Application in Women with Breast Cancer
Author(s): Rebecca Lehman* and Colleen Jackson-Cook and Kellie J. Archer
Companies: Virginia Commonwealth University and Virginia Commonwealth University and Virginia Commonwealth University
Keywords: Discrete response ; Poisson Regresion ; Count data ; Longitudinal ; High-dimensional ; Genomic

Micronuclei (MN) are a measure of chromosomal instability indicative of genomic damage. Those that are formed by mutagens may play a role in carcinogenesis. MN frequency is determined by counting the number of binucleated cells with at least one MN in approximately 2,000 binucleated cells. To elucidate molecular mechanisms involved in DNA damage, we are interested in identifying genomic features associated with MN. When analyzing count data often methods that assume the underlying distribution is Gaussian are inappropriate. Although transformations could be applied it often is of interest to analyze the raw count data using Poisson regression. In high-throughput genomic experiments the number of samples does not exceed the number of explanatory variables thus traditional statistical methods cannot be applied. We present our extension of the Generalized Monotone Incremental Forward Stagewise Method to the longitudinal Poisson regression model. An application will be described predicting MN frequencies recorded at 5 time points collected during the treatment of breast cancer in women using the corresponding methylation levels of CpG sites.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association