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

Statistical inference for single-ind...

Lin, Wei.

Linked to FindBook

Google Book

Amazon

博客來

Statistical inference for single-index models.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Statistical inference for single-index models./
Author:	Lin, Wei.
Description:	149 p.
Notes:	Adviser: K. B. Kulasekera.
Contained By:	Dissertation Abstracts International67-05B.
Subject:	Mathematics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3215795
ISBN:	9780542674143

Statistical inference for single-index models.
Lin, Wei.

Statistical inference for single-index models. - 149 p.

Adviser: K. B. Kulasekera.

Thesis (Ph.D.)--Clemson University, 2006.

With the rapid increase in computing power, nonparametric methods in regression analysis have gained more and more popularity. One major difficulty in a general nonparametric regression model comes from the so-called "curse-of-dimensionality"; the difficulty and inefficiency of smoothing in high-dimensional settings. Hence, scientists seek techniques to reduce the model dimension in order to keep a reasonable level of accuracy for all practical purposes. The single-index model, where the regression function takes the form m(x) = g(theta' x), is a natural generalization of the classical linear regression models and a restrictive version of a completely nonparametric model. Most of the statistical analysis in the literature for the single-index models focuses on estimating the index vector theta and the link function g(·). In this work, we present some research results for the following issues regarding the single-index models. These are: the identifiability of the single-index models and their generalizations; the error variance estimation in the single-index models; testing for the equality of two single-index models; variable selection in a single-index model; and a goodness-of-fit (GOF) test for the single-index models (checking whether or not a sample follows a single-index model).

ISBN: 9780542674143Subjects--Topical Terms:

515831
Mathematics.

Statistical inference for single-index models.
LDR:02141nam 2200265 a 45 001 965414
005 20110906
008 110906s2006 eng d
020 $a 9780542674143
035 $a (UMI)AAI3215795
035 $a AAI3215795
040 $a UMI $c UMI
100 1 $a Lin, Wei. $3 1288190
245 1 0 $a Statistical inference for single-index models.
300 $a 149 p.
500 $a Adviser: K. B. Kulasekera.
500 $a Source: Dissertation Abstracts International, Volume: 67-05, Section: B, page: 2591.
502 $a Thesis (Ph.D.)--Clemson University, 2006.
520 $a With the rapid increase in computing power, nonparametric methods in regression analysis have gained more and more popularity. One major difficulty in a general nonparametric regression model comes from the so-called "curse-of-dimensionality"; the difficulty and inefficiency of smoothing in high-dimensional settings. Hence, scientists seek techniques to reduce the model dimension in order to keep a reasonable level of accuracy for all practical purposes. The single-index model, where the regression function takes the form m(x) = g(theta' x), is a natural generalization of the classical linear regression models and a restrictive version of a completely nonparametric model. Most of the statistical analysis in the literature for the single-index models focuses on estimating the index vector theta and the link function g(·). In this work, we present some research results for the following issues regarding the single-index models. These are: the identifiability of the single-index models and their generalizations; the error variance estimation in the single-index models; testing for the equality of two single-index models; variable selection in a single-index model; and a goodness-of-fit (GOF) test for the single-index models (checking whether or not a sample follows a single-index model).
590 $a School code: 0050.
650 4 $a Mathematics. $3 515831
690 $a 0405
710 2 0 $a Clemson University. $3 997173
773 0 $t Dissertation Abstracts International $g 67-05B.
790 $a 0050
790 1 0 $a Kulasekera, K. B., $e advisor
791 $a Ph.D.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3215795