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

Model selection for unbiased estimat...

Liu, Xiangyang.

Linked to FindBook

Google Book

Amazon

博客來

Model selection for unbiased estimating equations.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Model selection for unbiased estimating equations./
Author:	Liu, Xiangyang.
Description:	152 p.
Notes:	Adviser: Martin A. Tanner.
Contained By:	Dissertation Abstracts International61-11B.
Subject:	Statistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9994691
ISBN:	0493021485

Model selection for unbiased estimating equations.
Liu, Xiangyang.

Model selection for unbiased estimating equations. - 152 p.

Adviser: Martin A. Tanner.

Thesis (Ph.D.)--Northwestern University, 2000.

We consider model selection based on estimators that are asymptotically normal. Such a method can be applied to the context of estimating equations, since a full specification of the probability model or likelihood function is not required. We construct a class of “cost” functions for the models in consideration, and show that the minimizer of the cost function is a consistent estimator of the model under suitable conditions. One special cost function is closely related to the Bayes factor and Schwarz's Bayesian Information Criterion (BIC). We also show that by ranking the Z-statistics, the scope of model searching can be greatly reduced. The proposed methodology can be applied to both linear and some nonlinear models. The convergence rate of the newly proposed model selection criteria is explored as well. In addition to the simulation results, we also provide data analysis examples, and illustrate the use of these variable selection techniques in the contexts of linear regressions, partial likelihood analysis and the generalized estimating equations.

ISBN: 0493021485Subjects--Topical Terms:

517247
Statistics.

Model selection for unbiased estimating equations.
LDR:01913nam 2200265 a 45 001 929312
005 20110427
008 110427s2000 eng d
020 $a 0493021485
035 $a (UnM)AAI9994691
035 $a AAI9994691
040 $a UnM $c UnM
100 1 $a Liu, Xiangyang. $3 1252796
245 1 0 $a Model selection for unbiased estimating equations.
300 $a 152 p.
500 $a Adviser: Martin A. Tanner.
500 $a Source: Dissertation Abstracts International, Volume: 61-11, Section: B, page: 5948.
502 $a Thesis (Ph.D.)--Northwestern University, 2000.
520 $a We consider model selection based on estimators that are asymptotically normal. Such a method can be applied to the context of estimating equations, since a full specification of the probability model or likelihood function is not required. We construct a class of “cost” functions for the models in consideration, and show that the minimizer of the cost function is a consistent estimator of the model under suitable conditions. One special cost function is closely related to the Bayes factor and Schwarz's Bayesian Information Criterion (BIC). We also show that by ranking the Z-statistics, the scope of model searching can be greatly reduced. The proposed methodology can be applied to both linear and some nonlinear models. The convergence rate of the newly proposed model selection criteria is explored as well. In addition to the simulation results, we also provide data analysis examples, and illustrate the use of these variable selection techniques in the contexts of linear regressions, partial likelihood analysis and the generalized estimating equations.
590 $a School code: 0163.
650 4 $a Statistics. $3 517247
690 $a 0463
710 2 0 $a Northwestern University. $3 1018161
773 0 $t Dissertation Abstracts International $g 61-11B.
790 $a 0163
790 1 0 $a Tanner, Martin A., $e advisor
791 $a Ph.D.
792 $a 2000
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9994691