東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Design and analysis of DNA microarra...

Li, Li.

FindBook

Google Book

Amazon

博客來

Design and analysis of DNA microarray data: Model validation and sensitivity analysis with an application in bioequivalence.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Design and analysis of DNA microarray data: Model validation and sensitivity analysis with an application in bioequivalence./
作者:	Li, Li.
面頁冊數:	133 p.
附註:	Source: Dissertation Abstracts International, Volume: 65-10, Section: B, page: 5220.
Contained By:	Dissertation Abstracts International65-10B.
標題:	Statistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3151012
ISBN:	049610747X

Design and analysis of DNA microarray data: Model validation and sensitivity analysis with an application in bioequivalence.
Li, Li.

Design and analysis of DNA microarray data: Model validation and sensitivity analysis with an application in bioequivalence. - 133 p.

Source: Dissertation Abstracts International, Volume: 65-10, Section: B, page: 5220.

Thesis (Ph.D.)--Temple University, 2004.

In clinical development, genomic studies are usually conducted to determine whether there is an association between pharmacogenomic markers and clinical outcomes. If there is a statistically significant association, a predictive model is established to identify patients who are most likely to respond to the test treatment. However, the United States Food and Drug Administration (FDA) requires that such a predictive model be validated before it can be used in clinical development. For this purpose, cross-validation methods are usually considered.

ISBN: 049610747XSubjects--Topical Terms:

517247
Statistics.

Design and analysis of DNA microarray data: Model validation and sensitivity analysis with an application in bioequivalence.
LDR:03457nmm 2200313 4500 001 1839618
005 20050624104422.5
008 130614s2004 eng d
020 $a 049610747X
035 $a (UnM)AAI3151012
035 $a AAI3151012
040 $a UnM $c UnM
100 1 $a Li, Li. $3 1036040
245 1 0 $a Design and analysis of DNA microarray data: Model validation and sensitivity analysis with an application in bioequivalence.
300 $a 133 p.
500 $a Source: Dissertation Abstracts International, Volume: 65-10, Section: B, page: 5220.
500 $a Chairs: Woollcott Smith; Shein-Chung Chow.
502 $a Thesis (Ph.D.)--Temple University, 2004.
520 $a In clinical development, genomic studies are usually conducted to determine whether there is an association between pharmacogenomic markers and clinical outcomes. If there is a statistically significant association, a predictive model is established to identify patients who are most likely to respond to the test treatment. However, the United States Food and Drug Administration (FDA) requires that such a predictive model be validated before it can be used in clinical development. For this purpose, cross-validation methods are usually considered.
520 $a Shao (1993) proposed cross-validation method for selecting a model having the best predictive ability among a class of linear models with equal variances. In practice, a number of studies are usually conducted at different laboratories using similar but different technologies by different analysts for obtaining sufficient genomic data. Different studies may exhibit different variabilities due to different experimental conditions. Thus, Shao's method for cross-validation is necessarily modified.
520 $a In this thesis, two re-sampling methods are proposed to account for heterogeneity of variance across studies for selecting a correct model. Several simulations were conducted to evaluate the finite sample performance of the two re-sampling methods for cross-validation of a linear model with unequal variances. The results indicate that the heterogeneity of variances across studies has an impact on the probability of correctly selecting the true model. Furthermore, we have the following observations: (1) The probability of correctly selecting the true model decreases as the degree of heterogeneity in variance increases; (2) The approach works better when the number of independent variables is small. An example concerning a breast cancer research is presented to illustrate the use of the proposed methods.
520 $a Also included in this thesis is a sensitivity analysis with an application in bioequivalence. The sensitivity index is considered a useful measure of the sensitivity of an established predictive model in terms of reproducibility of clinical response. We attempt to use the genomic prediction as a surrogate for the pharmacokinetic response in assessing bioequivalence. Along this line, the methods for assessment of average, population, and individual bioequivalence based on the sensitivity analysis are studied. Some examples are given to illustrate the proposed methods.
590 $a School code: 0225.
650 4 $a Statistics. $3 517247
690 $a 0463
710 2 0 $a Temple University. $3 959342
773 0 $t Dissertation Abstracts International $g 65-10B.
790 1 0 $a Smith, Woollcott, $e advisor
790 1 0 $a Chow, Shein-Chung, $e advisor
790 $a 0225
791 $a Ph.D.
792 $a 2004
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3151012