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

Two-way latent variable clustering.

Song, Yang.

FindBook

Google Book

Amazon

博客來

Two-way latent variable clustering.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Two-way latent variable clustering./
作者:	Song, Yang.
面頁冊數:	163 p.
附註:	Source: Dissertation Abstracts International, Volume: 66-05, Section: B, page: 2663.
Contained By:	Dissertation Abstracts International66-05B.
標題:	Statistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3175552
ISBN:	0542142171

Two-way latent variable clustering.
Song, Yang.

Two-way latent variable clustering. - 163 p.

Source: Dissertation Abstracts International, Volume: 66-05, Section: B, page: 2663.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2005.

We propose a two-way latent variable clustering (LVC) method to extend finite mixture models as the basis for a general model-based clustering framework. We show how one-way latent variable clustering on subjects extends finite mixture models to allow unbalanced feature-by-subject data matrices, using an EM algorithm to find maximum likelihood estimates (MLE) of model parameters. We then develop a two-way LVC method that simultaneously clusters subjects and features. We use Gibbs sampler in the E-step and resort to stochastic versions of EM algorithms to estimate model parameters, if neither cluster structure of subjects nor that of features is known a priori. Inference of cluster structure focuses on the posterior distribution of latent variables for subjects and features given MLE of model parameters.

ISBN: 0542142171Subjects--Topical Terms:

517247
Statistics.

Two-way latent variable clustering.
LDR:02916nmm 2200313 4500 001 1817528
005 20060814143912.5
008 130610s2005 eng d
020 $a 0542142171
035 $a (UnM)AAI3175552
035 $a AAI3175552
040 $a UnM $c UnM
100 1 $a Song, Yang. $3 1265217
245 1 0 $a Two-way latent variable clustering.
300 $a 163 p.
500 $a Source: Dissertation Abstracts International, Volume: 66-05, Section: B, page: 2663.
500 $a Supervisor: Brian S. Yandell.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2005.
520 $a We propose a two-way latent variable clustering (LVC) method to extend finite mixture models as the basis for a general model-based clustering framework. We show how one-way latent variable clustering on subjects extends finite mixture models to allow unbalanced feature-by-subject data matrices, using an EM algorithm to find maximum likelihood estimates (MLE) of model parameters. We then develop a two-way LVC method that simultaneously clusters subjects and features. We use Gibbs sampler in the E-step and resort to stochastic versions of EM algorithms to estimate model parameters, if neither cluster structure of subjects nor that of features is known a priori. Inference of cluster structure focuses on the posterior distribution of latent variables for subjects and features given MLE of model parameters.
520 $a We then study model selection for one-way and two-way LVC models. We extend the integrated complete-data likelihood (ICL) criterion from finite mixture models to LVC models. Based on observation prediction error, we propose to use mean absolute error (MAE) and root mean square error (RMSE) on a randomly selected subset of data as two other model selection criteria.
520 $a Cluster structure of new subjects and/or new features in new data can be predicted with LVC models, which has various practical applications. We can use LVC models in classification with a priori known cluster information; to investigate cluster structure by training an LVC model on a random subset of data; and to predict missing observations based on cluster structure and apply to collaborative filtering.
520 $a In summary, we have developed a two-way latent variable clustering methodology that is applicable to a variety of problems under a coherent framework. In simulated data the method works well. In real data we show that our method is comparable to, and in some cases better than, other methods with case studies in collaborative filtering and both clustering and classification of microarray gene expression data.
590 $a School code: 0262.
650 4 $a Statistics. $3 517247
650 4 $a Biology, Biostatistics. $3 1018416
690 $a 0463
690 $a 0308
710 2 0 $a The University of Wisconsin - Madison. $3 626640
773 0 $t Dissertation Abstracts International $g 66-05B.
790 1 0 $a Yandell, Brian S., $e advisor
790 $a 0262
791 $a Ph.D.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3175552