東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

On Bayesian modeling and design for ...

Ji, Yuan.

Linked to FindBook

Google Book

Amazon

博客來

On Bayesian modeling and design for microarray gene expression data.

Record Type:	Electronic resources : Monograph/item
Title/Author:	On Bayesian modeling and design for microarray gene expression data./
Author:	Ji, Yuan.
Description:	112 p.
Notes:	Source: Dissertation Abstracts International, Volume: 64-08, Section: B, page: 3889.
Contained By:	Dissertation Abstracts International64-08B.
Subject:	Statistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3101396

On Bayesian modeling and design for microarray gene expression data.
Ji, Yuan.

On Bayesian modeling and design for microarray gene expression data. - 112 p.

Source: Dissertation Abstracts International, Volume: 64-08, Section: B, page: 3889.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2003.

Three problems related to microarray experiments are considered in this thesis. Two of them deal with the statistical modeling and inferences and the other is related to the design of experiments.Subjects--Topical Terms:

517247
Statistics.

On Bayesian modeling and design for microarray gene expression data.
LDR:03059nmm 2200313 4500 001 1856167
005 20040621100420.5
008 130614s2003 eng d
035 $a (UnM)AAI3101396
035 $a AAI3101396
040 $a UnM $c UnM
100 1 $a Ji, Yuan. $3 1943953
245 1 0 $a On Bayesian modeling and design for microarray gene expression data.
300 $a 112 p.
500 $a Source: Dissertation Abstracts International, Volume: 64-08, Section: B, page: 3889.
500 $a Supervisors: Kyungmann Kim; Kam-Wah Tsui.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2003.
520 $a Three problems related to microarray experiments are considered in this thesis. Two of them deal with the statistical modeling and inferences and the other is related to the design of experiments.
520 $a The first problem is about classification of experimental samples or tissues with gene expression profiles. Because the number of gene expression levels is much larger than the number of treatments to be classified, some traditional methods such as the Fisher discriminant analysis cannot be directly applied. We propose a two-stage empirical Bayes classification method for this problem. The first stage combines genes into clusters and the second stage constructs an empirical Bayes model incorporating the cluster information of genes. The performance of our method is evaluated by simulation studies. The method is implemented for two real data sets and misclassification errors are adjusted for the selection bias.
520 $a The second problem deals with identification of differentially expressed genes. We group genes into clusters again as a preliminary step to simplify the modeling process later. The differential expression level is modeled by a gene specific parameter and the posterior distribution for this parameter is obtained for each gene. Differential expression is declared based on the rank of posterior means. To assess the sensitivity and specificity of the set of genes declared to be differentially expressed, posterior selection probabilities are computed with a Monte Carlo procedure.
520 $a In the third problem, we address the pooling issue in the design of microarray experiments. Whether or not to pool mRNA samples from different subjects for subsequent analysis is an important design issue in microarray experiments. Motivated by Kendziorski <italic>et al</italic>. (2003), we extend their results for comparing pooled design and non-pooled design by relaxing several modeling assumptions. We further develop a general model that accounts for the variation in the pooling of mRNA samples. We employ a Monte Carlo method to compute the mean square error of the Bayesian estimate.
590 $a School code: 0262.
650 4 $a Statistics. $3 517247
650 4 $a Biology, Genetics. $3 1017730
690 $a 0463
690 $a 0369
710 2 0 $a The University of Wisconsin - Madison. $3 626640
773 0 $t Dissertation Abstracts International $g 64-08B.
790 1 0 $a Kim, Kyungmann, $e advisor
790 1 0 $a Tsui, Kam-Wah, $e advisor
790 $a 0262
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3101396