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

切換: 標籤 | MARC模式 | ISBD

Lassoing mixtures and Bayesian robus...

Xing, Guan.

FindBook

Google Book

Amazon

博客來

Lassoing mixtures and Bayesian robust estimation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Lassoing mixtures and Bayesian robust estimation./
作者:	Xing, Guan.
面頁冊數:	133 p.
附註:	Source: Dissertation Abstracts International, Volume: 67-10, Section: B, page: 5498.
Contained By:	Dissertation Abstracts International67-10B.
標題:	Biology, Biostatistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3237856
ISBN:	9780542928499

Lassoing mixtures and Bayesian robust estimation.
Xing, Guan.

Lassoing mixtures and Bayesian robust estimation. - 133 p.

Source: Dissertation Abstracts International, Volume: 67-10, Section: B, page: 5498.

Thesis (Ph.D.)--Case Western Reserve University, 2007.

This dissertation includes two parts. The first part describes a new estimation method for finite mixture models. Different from traditional methods, we borrow ideas from the variable selection approaches in linear models. After generating the pseudo-response from a saturated mixture model and constructing predictors using candidate component densities, we transform the mixture model density estimation problem to a variable selection problem in linear models. Using a variant of the LASSO constraint approach, we can do component number selection and parameter estimation simultaneously for finite mixture models. The performance of this method is illustrated with simulated data and some well-known real data sets.

ISBN: 9780542928499Subjects--Topical Terms:

1018416
Biology, Biostatistics.

Lassoing mixtures and Bayesian robust estimation.
LDR:02361nmm 2200277 4500 001 1833761
005 20071112133555.5
008 130610s2007 eng d
020 $a 9780542928499
035 $a (UMI)AAI3237856
035 $a AAI3237856
040 $a UMI $c UMI
100 1 $a Xing, Guan. $3 1922445
245 1 0 $a Lassoing mixtures and Bayesian robust estimation.
300 $a 133 p.
500 $a Source: Dissertation Abstracts International, Volume: 67-10, Section: B, page: 5498.
500 $a Adviser: J. Sunil Rao.
502 $a Thesis (Ph.D.)--Case Western Reserve University, 2007.
520 $a This dissertation includes two parts. The first part describes a new estimation method for finite mixture models. Different from traditional methods, we borrow ideas from the variable selection approaches in linear models. After generating the pseudo-response from a saturated mixture model and constructing predictors using candidate component densities, we transform the mixture model density estimation problem to a variable selection problem in linear models. Using a variant of the LASSO constraint approach, we can do component number selection and parameter estimation simultaneously for finite mixture models. The performance of this method is illustrated with simulated data and some well-known real data sets.
520 $a In the second part, we deal with the estimation with the contaminated data. Traditional Bayesian approaches use the variance-inflation model or the mean-shift model. We extend the Bayesian contaminated model to the general case without assuming a specific distribution for the potential outliers, but using a constructed reference population to draw random samples. With the proposed latent indicator variables for each observation, we construct a Bayesian hierarchical model and use Gibbs sampler to draw posterior samples. The parameter inference based on the Gibbs samples is robust, and a series of simulations and classic real data analysis indicate the better performance of our methods than other approaches in linear models, generalized linear models and density estimation.
590 $a School code: 0042.
650 4 $a Biology, Biostatistics. $3 1018416
690 $a 0308
710 2 0 $a Case Western Reserve University. $3 1017714
773 0 $t Dissertation Abstracts International $g 67-10B.
790 1 0 $a Rao, J. Sunil, $e advisor
790 $a 0042
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3237856