Minimum Information Loss Cluster Analysis for Categorical Data

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F06%3A00125818" target="_blank" >RIV/68407700:21340/06:00125818 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Minimum Information Loss Cluster Analysis for Categorical Data

Original language description

The EM algorithm has been used repeatedly to identify latent classes in categorical data by estimating finite distribution mixtures of product components. Unfortunately, the underlying mixtures are not uniquely identifiable and moreover, the estimated mixture parameters are starting-point dependent. For this reason we assume the latent class model only to define a set of elementary properties and the related statistical decision problem. In order to avoid the problem of unique identification of latent classes we propose a hierarchical ``bottom up'' cluster analysis based on unifying the latent classes sequentially. The clustering procedure is controlled by minimum information loss criterion.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

BA - General mathematics

OECD FORD branch

—

Project

—

Continuities

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Publication year

2006

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Doktorandské dny 2006

ISBN

80-01-03554-9

ISSN

—

e-ISSN

—

Number of pages

12

Pages from-to

—

Publisher name

Česká technika - nakladatelství ČVUT

Place of publication

Praha

Event location

Praha

Event date

Nov 10, 2006

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

—