Activity Number:
|
15
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 11, 2002 : 2:00 PM to 3:50 PM
|
Sponsor:
|
ENAR
|
Abstract - #300958 |
Title:
|
On the Optimal Design of Gene Expression Microarray Experiments
|
Author(s):
|
Xiao Yang*+ and Keying Ye and Ina Hoeschele
|
Affiliation(s):
|
Virginia Polytechnic Institute and State University and Virginia Polytechnic Institute and State University and Virginia Polytechnic Institute and State University
|
Address:
|
503 E, Hutchesion Hall, Blacksburg, Virginia, 24060, USA
|
Keywords:
|
optimal block design ; microarray experiment ; mixed design ; non-orthogonality
|
Abstract:
|
DNA microarray experiments are part of a new class of biotechnologies which allow the monitoring of expression levels for thousands of genes simultaneously. Gene expression experiments based on microarrays identify genes involved in complex disease or multifactorial traits by comparing expression levels of genes in different tissue samples. The reference and loop design have been widely used in design of microarray experiment. Reference design is not favored, due to the confounding between dye and variety effects while loop design becomes less efficient when the number of varieties exceeds eight. In this paper, the problem of optimal incomplete block design with block size of two is considered when there are a small number of blocks available. A new class of designs, the mixed design, which is a mixture of reference and loop design, are identified and their optimality has been proved in terms of A- and E-optimality criteria. Due to the non-orthogonal structure of such designs, we also provide details regarding analysis of gene expression data from microarray experiments based upon the mixed designs.
|
- 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 2002 program |