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

Bayesian Quantile Regression in Late...

Wang, Yifan,

Linked to FindBook

Google Book

Amazon

博客來

Bayesian Quantile Regression in Latent Variable Models /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Bayesian Quantile Regression in Latent Variable Models // Yifan Wang.
Author:	Wang, Yifan,
Description:	1 electronic resource (115 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 78-08, Section: B.
Contained By:	Dissertations Abstracts International78-08B.
Subject:	Statistics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10307359
ISBN:	9781369519334

Bayesian Quantile Regression in Latent Variable Models /
Wang, Yifan,

Bayesian Quantile Regression in Latent Variable Models /Yifan Wang. - 1 electronic resource (115 pages)

Source: Dissertations Abstracts International, Volume: 78-08, Section: B.

Quantile regression is a popular method that has been introduced to a wide range of models in statistics and econometrics. Compared to the mean regression, quantile regression provides a complete description of the relationship between the response and the predictors. However, despite its popularity, quantile regression has been rarely studied in latent variable models, which are useful in the analysis of variables that cannot be directly measured. In this thesis, the Bayesian quantile regression approach based upon the asymmetric Laplace distribution is developed in two kinds of latent variable models, including structural equation models (SEMs) and varying coefficient models with random effects, which have not been proposed before. Apart from coefficients estimation, the variable selection using regularization methods, including Bayesian Lasso and Bayesian adaptive Lasso, is also considered. Full Markov Chain Monte Carlo (MCMC) algorithms with Gibbs sampling method are derived for the Bayesian inference. Simulation studies demonstrate that performance of the proposed methods are satisfactory. We also utilize the proposed methods in several real data examples in medical science and econometrics to provide a deeper insight of the interrelationship among the variables.

English

ISBN: 9781369519334Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Markov Chain Monte Carlo algorithms

Bayesian Quantile Regression in Latent Variable Models /
LDR:02738nmm a22004213i 4500 001 2430852
005 20250605050524.5
006 m o d
007 cr|nu||||||||
008 261011s2016 miu||||||m |||||||eng d
020 $a 9781369519334
035 $a (MiAaPQD)AAI10307359
035 $a AAI10307359
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Wang, Yifan, $e author. $3 3819378
245 1 0 $a Bayesian Quantile Regression in Latent Variable Models / $c Yifan Wang.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2016
300 $a 1 electronic resource (115 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 78-08, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Includes supplementary digital materials.
500 $a Advisors: Song, Xinyuan.
502 $b Ph.D. $c The Chinese University of Hong Kong (Hong Kong) $d 2016.
520 $a Quantile regression is a popular method that has been introduced to a wide range of models in statistics and econometrics. Compared to the mean regression, quantile regression provides a complete description of the relationship between the response and the predictors. However, despite its popularity, quantile regression has been rarely studied in latent variable models, which are useful in the analysis of variables that cannot be directly measured. In this thesis, the Bayesian quantile regression approach based upon the asymmetric Laplace distribution is developed in two kinds of latent variable models, including structural equation models (SEMs) and varying coefficient models with random effects, which have not been proposed before. Apart from coefficients estimation, the variable selection using regularization methods, including Bayesian Lasso and Bayesian adaptive Lasso, is also considered. Full Markov Chain Monte Carlo (MCMC) algorithms with Gibbs sampling method are derived for the Bayesian inference. Simulation studies demonstrate that performance of the proposed methods are satisfactory. We also utilize the proposed methods in several real data examples in medical science and econometrics to provide a deeper insight of the interrelationship among the variables.
546 $a English
590 $a School code: 1307
650 4 $a Statistics. $3 517247
653 $a Markov Chain Monte Carlo algorithms
653 $a Quantile regression
653 $a Structural equation models
653 $a Varying coefficient models
690 $a 0463
710 2 $a The Chinese University of Hong Kong (Hong Kong). $e degree granting institution. $3 3765695
720 1 $a Song, Xinyuan $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 78-08B.
790 $a 1307
791 $a Ph.D.
792 $a 2016
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10307359