|
Activity Number:
|
474
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305414 |
|
Title:
|
Model-Based Classifications for Multiple Conditions on the Temporal Gene Expressions
|
|
Author(s):
|
Dianliang Deng*+
|
|
Companies:
|
University of Regina
|
|
Address:
|
Department of Mathematics and Statistics, Regina, SK, S4V 2X3, Canada
|
|
Keywords:
|
Chi-square test ; Classification ; Longitudinal data analysis, ; Mahalanobis distance ; Non-linear regression analysis ; Temporal gene expression
|
|
Abstract:
|
Temporal gene expression data are of particular interest as it contains rich information in characterization of gene function and have been widely used in biomedical studies and cancer early detection. In this talk, we will to investigate the effects of multiple conditions to the gene expressions and then classify the conditions according to the obtained results on their effects to the gene profiles. We propose a non-linear regression model to characterize the variance function of genes under a give condition. Then, based on the parameter estimates, a chi-square test is proposed to test the equality of conditions. Furthermore, the Mahalanobis distance is used for the classification of conditions. The proposed methods are applied to the data set with 32 genes under 39 biological conditions. The simulation shows that our methods are well performed for the classifications of conditions.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
