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

Optimal or balanced experimental des...

Temple University.

Linked to FindBook

Google Book

Amazon

博客來

Optimal or balanced experimental designs under dependence.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Optimal or balanced experimental designs under dependence./
Author:	Sethuraman, Venkat S.
Description:	101 p.
Notes:	Adviser: Damaraju Raghavarao.
Contained By:	Dissertation Abstracts International69-01B.
Subject:	Biology, Biostatistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3300377
ISBN:	9780549447054

Optimal or balanced experimental designs under dependence.
Sethuraman, Venkat S.

Optimal or balanced experimental designs under dependence. - 101 p.

Adviser: Damaraju Raghavarao.

Thesis (Ph.D.)--Temple University, 2008.

This research work is focused on the optimal factorial and fractional-factorial designs when observations within blocks are correlated. The topic for this dissertation was motivated by a problem where the pharmaceutical experimenter needed to develop a controlled release, once-daily tablet formulation. Typically, in order to compare different formulations, trials are conducted in healthy human volunteers where each formulation is administered and bioavailability is estimated. Since each subject is administered more than one formulation, the observations within subjects are correlated.

ISBN: 9780549447054Subjects--Topical Terms:

1018416
Biology, Biostatistics.

Optimal or balanced experimental designs under dependence.
LDR:03098nmm 2200313 a 45 001 867066
005 20100802
008 100802s2008 ||||||||||||||||| ||eng d
020 $a 9780549447054
035 $a (UMI)AAI3300377
035 $a AAI3300377
040 $a UMI $c UMI
100 1 $a Sethuraman, Venkat S. $3 1035769
245 1 0 $a Optimal or balanced experimental designs under dependence.
300 $a 101 p.
500 $a Adviser: Damaraju Raghavarao.
500 $a Source: Dissertation Abstracts International, Volume: 69-01, Section: B, page: 0399.
502 $a Thesis (Ph.D.)--Temple University, 2008.
520 $a This research work is focused on the optimal factorial and fractional-factorial designs when observations within blocks are correlated. The topic for this dissertation was motivated by a problem where the pharmaceutical experimenter needed to develop a controlled release, once-daily tablet formulation. Typically, in order to compare different formulations, trials are conducted in healthy human volunteers where each formulation is administered and bioavailability is estimated. Since each subject is administered more than one formulation, the observations within subjects are correlated.
520 $a We have characterized D-optimal designs for s n symmetric factorial experiments when observations within blocks are correlated. In Chapter 3, compound symmetry correlation structure within blocks is discussed. We have provided an explicit construction of D-optimal designs for sn factorial experiments with blocks of size s or multiples of s. The construction of optimal designs for 2n factorial experiments is discussed in detail. It often happens that one or more observations from the factorial experiment may be missing. The problem where missing values are confined to one block has been discussed.
520 $a In Chapter 4, auto-correlation error structure is discussed. Balanced designs for 2n factorial experiments have been characterized, when observations within blocks are spatially correlated, AR(1) with positive correlation (rho > 0). An explicit construction of balanced designs for both 2n full and 2 n-1 fractional factorial experiments has been presented.
520 $a In Chapter 5, response surface designs under dependence (auto correlation error structure) has been considered. The structure of X'X matrix under independence (where X is the design matrix) is known. In our construction, sufficient conditions have been provided to achieve this structure under dependence. The construction has been illustrated using examples of a Central Composite Design (CCD) for n = 2 and n = 3, which are rotatable. Similarly among the class of Box-Behnken Design (BBH), we have considered designs for n = 4 in 6 blocks and n = 7 in 7 blocks constructed using the concepts of balanced incomplete block designs.
590 $a School code: 0225.
650 4 $a Biology, Biostatistics. $3 1018416
650 4 $a Statistics. $3 517247
690 $a 0308
690 $a 0463
710 2 $a Temple University. $3 959342
773 0 $t Dissertation Abstracts International $g 69-01B.
790 $a 0225
790 1 0 $a Raghavarao, Damaraju, $e advisor
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3300377