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 到查詢結果 [ subject:"Statistics" ]

切換: 標籤 | MARC模式 | ISBD

Sequential design of computer experi...

Lehman, Jeffrey Scott.

FindBook

Google Book

Amazon

博客來

Sequential design of computer experiments for robust parameter design.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Sequential design of computer experiments for robust parameter design./
作者:	Lehman, Jeffrey Scott.
面頁冊數:	159 p.
附註:	Advisers: William I. Notz; Thomas J. Santner.
Contained By:	Dissertation Abstracts International63-08B
標題:	Statistics -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3062647
ISBN:	0493789480

Sequential design of computer experiments for robust parameter design.
Lehman, Jeffrey Scott.

Sequential design of computer experiments for robust parameter design. - 159 p.

Advisers: William I. Notz; Thomas J. Santner.

Thesis (Ph.D.)--The Ohio State University, 2002.

Many physical systems can be modeled mathematically so that “responses” are computable at arbitrary “experimental” inputs using numerical methods implemented by a complex computer code. In some cases, such computer codes allow us to conduct analogs of physical experiments that would not be possible due to the complexity of the required physical system, cost of the physical experiment, or time constraints. In a computer experiment, a response, <italic> y</italic>(<bolditalic>x</bolditalic>), usually deterministic, is computed for each set of input variables, <bolditalic>x</bolditalic>, according to some experimental design strategy. Then, as in physical experiments, the relationship between <bolditalic>x</bolditalic>, the inputs, and <italic>y</italic>(<bolditalic> x</bolditalic>), the outputs, is studied.

ISBN: 0493789480Subjects--Topical Terms:

773967
Statistics

Sequential design of computer experiments for robust parameter design.
LDR:03464nam 2200289 a 45 001 936673
005 20110510
008 110510s2002 eng d
020 $a 0493789480
035 $a (UnM)AAI3062647
035 $a AAI3062647
040 $a UnM $c UnM
100 1 $a Lehman, Jeffrey Scott. $3 1260481
245 1 0 $a Sequential design of computer experiments for robust parameter design.
300 $a 159 p.
500 $a Advisers: William I. Notz; Thomas J. Santner.
500 $a Source: Dissertation Abstracts International, Volume: 63-08, Section: B, page: 3776.
502 $a Thesis (Ph.D.)--The Ohio State University, 2002.
520 $a Many physical systems can be modeled mathematically so that “responses” are computable at arbitrary “experimental” inputs using numerical methods implemented by a complex computer code. In some cases, such computer codes allow us to conduct analogs of physical experiments that would not be possible due to the complexity of the required physical system, cost of the physical experiment, or time constraints. In a computer experiment, a response, <italic> y</italic>(<bolditalic>x</bolditalic>), usually deterministic, is computed for each set of input variables, <bolditalic>x</bolditalic>, according to some experimental design strategy. Then, as in physical experiments, the relationship between <bolditalic>x</bolditalic>, the inputs, and <italic>y</italic>(<bolditalic> x</bolditalic>), the outputs, is studied.
520 $a We are concerned with the design of computer experiments when there are two types of inputs: control variables, <bolditalic>x</bolditalic><italic> c</italic>, and environmental variables, <bolditalic>x</bolditalic><italic> e</italic>. Control variables are set by a product designer and environmental variables are those that are not controlled in the field but have some probability distribution characterizing a population of interest. Our interest is in the mean response μ(<bolditalic>x</bolditalic><italic>c</italic>) = E[<italic>y</italic>(<bolditalic>x</bolditalic><italic>c</italic>, <bolditalic> X</bolditalic><italic>e</italic>)] as a function of the control variables, where the expectation is taken over the distribution of the environmental variables. The goal is to find a robust choice of control variables. We review different methods of defining robustness and focus on finding a set of control variables at which the response is insensitive to the value of the environmental variables. Such a choice ensures that the mean response is insensitive to perturbations of the nominal environmental variable distribution. We present a sequential strategy to select the inputs at which to observe the response so as to determine a robust setting of the control variables. Our solution is Bayesian; the prior takes the response as a draw from a stationary Gaussian stochastic process. The idea of the sequential algorithm is to compute the “improvement” over the current optimal robust setting for each untested site given the previous information; the design selects the next site to maximize an expected improvement
590 $a School code: 0168
650 $a Statistics $3 773967
690 $a 046
710 2 $a The Ohio State University $3 1260482
773 0 $t Dissertation Abstracts International $g 63-08B
790 $a 016
790 1 $a Notz, William I., $e adviso
790 1 $a Santner, Thomas J., $e adviso
791 $a Ph.D
792 $a 200
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3062647