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

Applications of modern statistical m...

Wicker, James Eric.

Linked to FindBook

Google Book

Amazon

博客來

Applications of modern statistical methods to analysis of data in physical science.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Applications of modern statistical methods to analysis of data in physical science./
Author:	Wicker, James Eric.
Description:	258 p.
Notes:	Source: Dissertation Abstracts International, Volume: 67-04, Section: B, page: 2036.
Contained By:	Dissertation Abstracts International67-04B.
Subject:	Statistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3214431
ISBN:	9780542638961

Applications of modern statistical methods to analysis of data in physical science.
Wicker, James Eric.

Applications of modern statistical methods to analysis of data in physical science. - 258 p.

Source: Dissertation Abstracts International, Volume: 67-04, Section: B, page: 2036.

Thesis (Ph.D.)--The University of Tennessee, 2006.

Modern methods of statistical and computational analysis offer solutions to dilemmas confronting researchers in physical science. Although the ideas behind modern statistical and computational analysis methods were originally introduced in the 1970's, most scientists still rely on methods written during the early era of computing. These researchers, who analyze increasingly voluminous and multivariate data sets, need modern analysis methods to extract the best results from their studies.

ISBN: 9780542638961Subjects--Topical Terms:

517247
Statistics.

Applications of modern statistical methods to analysis of data in physical science.
LDR:03444nmm 2200313 4500 001 1829325
005 20071107102519.5
008 130610s2006 eng d
020 $a 9780542638961
035 $a (UMI)AAI3214431
035 $a AAI3214431
040 $a UMI $c UMI
100 1 $a Wicker, James Eric. $3 1918191
245 1 0 $a Applications of modern statistical methods to analysis of data in physical science.
300 $a 258 p.
500 $a Source: Dissertation Abstracts International, Volume: 67-04, Section: B, page: 2036.
500 $a Adviser: William E. Blass.
502 $a Thesis (Ph.D.)--The University of Tennessee, 2006.
520 $a Modern methods of statistical and computational analysis offer solutions to dilemmas confronting researchers in physical science. Although the ideas behind modern statistical and computational analysis methods were originally introduced in the 1970's, most scientists still rely on methods written during the early era of computing. These researchers, who analyze increasingly voluminous and multivariate data sets, need modern analysis methods to extract the best results from their studies.
520 $a The first section of this work showcases applications of modern linear regression. Since the 1960's, many researchers in spectroscopy have used classical stepwise regression techniques to derive molecular constants. However, problems with thresholds of entry and exit for model variables plagues this analysis method. Other criticisms of this kind of stepwise procedure include its inefficient searching method, the order in which variables enter or leave the model and problems with overfitting data. We implement an information scoring technique that overcomes the assumptions inherent in the stepwise regression process to calculate molecular model parameters. We believe that this kind of information based model evaluation can be applied to more general analysis situations in physical science.
520 $a The second section proposes new methods of multivariate cluster analysis. The K-means algorithm and the EM algorithm, introduced in the 1960's and 1970's respectively, formed the basis of multivariate cluster analysis methodology for many years. However, several shortcomings of these methods include strong dependence on initial seed values and inaccurate results when the data seriously depart from hypersphericity. We propose new cluster analysis methods based on genetic algorithms that overcomes the strong dependence on initial seed values. In addition, we propose a generalization of the Genetic K-means algorithm which can accurately identify clusters with complex hyperellipsoidal covariance structures. We then use this new algorithm in a genetic algorithm based Expectation-Maximization process that can accurately calculate parameters describing complex clusters in a mixture model routine. Using the accuracy of this GEM algorithm, we assign information scores to cluster calculations in order to best identify the number of mixture components in a multivariate data set. We will showcase how these algorithms can be used to process multivariate data from astronomical observations.
590 $a School code: 0226.
650 4 $a Statistics. $3 517247
650 4 $a Physics, General. $3 1018488
650 4 $a Computer Science. $3 626642
690 $a 0463
690 $a 0605
690 $a 0984
710 2 0 $a The University of Tennessee. $3 1022026
773 0 $t Dissertation Abstracts International $g 67-04B.
790 1 0 $a Blass, William E., $e advisor
790 $a 0226
791 $a Ph.D.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3214431