|
Activity Number:
|
393
- Genetic Data Analysis, What Could Possibly Go Wrong?
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 5, 2020 : 1:00 PM to 2:50 PM
|
|
Sponsor:
|
Section on Statistics in Genomics and Genetics
|
|
Abstract #309492
|
|
|
Title:
|
To Ignore or Not to Ignore: Dealing with Missing Gene Expression Data
|
|
Author(s):
|
Kwang-Youn A Kim*
|
|
Companies:
|
Northwestern University
|
|
Keywords:
|
msising;
prediction;
gene;
expression;
classification;
association
|
|
Abstract:
|
To predict how a patient will respond to treatment based on gene expression data is a popular method in classification problem. In short, tens of thousands of gene expression levels are measured and we identify a list of genes that are associated with and predictive of whether a patient will respond to a given treatment. Implicit in the analysis are the assumptions of complete data collection or data missing at random (MAR). But what if these assumptions are violated? Can we still accept the analysis results assuming that we have complete dataset without any missing values? In this talk, we will explore the issues surrounding missing data.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2020 program
|
