Online Program Home
My Program

Abstract Details

Activity Number: 310 - SPEED:Statistical Methods for GWAs, Genetics, Genomics, and Other Omics Studies, Part 2
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 9:25 AM to 10:10 AM
Sponsor: Biometrics Section
Abstract #307698
Title: A New Sparse Network Model for High-Throughput Count Data
Author(s): Caesar (Zexuan) Li* and Gang Li and Eric Kawaguchi
Companies: University of California, Los Angeles and UCLA and UCLA Department of Biostatistics
Keywords: Graphical models; Poisson graphical models; next generation sequencing data; regularization selection

When using high-throughput sequencing technologies to measure gene expression, researchers are often interested in constructing a sparse network model. One popular approach, Poisson Graphical LASSO (Allen 2013), is implemented by fitting L1 penalized regression model. However, it is well known that L0 penalized regression produces a more parsimonious and accurate model, compared to L1 penalized methods. In this research we developed a new L0 based Poisson graphical model, using cyclic coordinate-wise broken adaptive ridge regression. Performance of the model is evaluated and compared with some existing methods on both simulated and real data.

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

Back to the full JSM 2019 program