TITLE

# Mixture modelling for cluster analysis

AUTHOR(S)
McLachlan, G.J.; Chang, S.U.
PUB. DATE
October 2004
SOURCE
Statistical Methods in Medical Research;Oct2004, Vol. 13 Issue 5, p347
SOURCE TYPE
DOC. TYPE
journal article
ABSTRACT
Cluster analysis via a finite mixture model approach is considered. With this approach to clustering, the data can be partitioned into a specified number of clusters g by first fitting a mixture model with g components. An outright clustering of the data is then obtained by assigning an observation to the component to which it has the highest estimated posterior probability of belonging; that is, the ith cluster consists of those observations assigned to the ith component (i = 1,..., g). The focus is on the use of mixtures of normal components for the cluster analysis of data that can be regarded as being continuous. But attention is also given to the case of mixed data, where the observations consist of both continuous and discrete variables.
ACCESSION #
14509726

## Related Articles

• Small deviation probabilities for positive random variables. Rozovsky, L. // Journal of Mathematical Sciences;Aug2006, Vol. 137 Issue 1, p4561

We deduce two lemmas that seem to be useful while studying small deviation probabilities for positive random variables. As an example, the so-called small balls problem is examined. Bibliography: 11 titles.

• A Strong Approximation Theorem for Quasi-associated Sequences. Wang, Wen // Acta Mathematica Sinica;Dec2005, Vol. 21 Issue 6, p1269

By combining the CsÃ¶rgÅ‘â€“RÃ©vÃ©sz quantile transform methods and the Skorohodâ€“Strassen martingale embedding theorem, we prove a strong approximation theorem for quasi-associated random variables with mean zero and finite (2+Î´)th moment under polynomial decay rate. As a...

• SEPARATION OF THE MAXIMA IN SAMPLES OF GEOMETRIC RANDOM VARIABLES. Brennan, Charlotte; Knopfmacher, Arnold; Mansour, Toufik; Wagner, Stephan // Applicable Analysis & Discrete Mathematics;2011, Vol. 5 Issue 2, p271

We consider samples of n geometric random variables Ï‰1 Ï‰2â€¦Ï‰n where P{Ï‰j = i} = pqi-1, for 1 â‰¤ j â‰¤ n, with p + q = 1. For each fixed integer d > 0, we study the probability that the distance between the consecutive maxima in these samples is at least d. We derive...

• A simple method for effective multi-site generation of stochastic hydrologic time series. Ilich, Nesa; Despotovic, Jovan // Stochastic Environmental Research & Risk Assessment;Feb2008, Vol. 22 Issue 2, p265

This paper presents an algorithm for generating stationary stochastic hydrologic time series at multiple sites. The ideas in this paper constitute a radical departure from commonly accepted methodologies. The approach relies on the recent advances in statistical science for simulating random...

• Mathematical Tools of Cluster Analysis. Trebuňa, Peter; Halčinová, Jana // Applied Mathematics;May2013, Vol. 4 Issue 5, p814

The paper deals with cluster analysis and comparison of clustering methods. Cluster analysis belongs to multivariate statistical methods. Cluster analysis is defined as general logical technique, procedure, which allows clustering variable objects into groups-clusters on the basis of similarity...

• Dollarization in Latin America: seigniorage costs and policy implications Lange, Carsten; Sauer, Christine // Quarterly Review of Economics & Finance;Sep2005, Vol. 45 Issue 4/5, p662

Abstract: This paper examines the seigniorage costs of official dollarization in 15 Latin American countries. We show that the total costs can be decomposed into two components: seigniorage transferred to the U.S. and seigniorage lost due to greater financial stability in the dollarized country....

• INTRAPOPULATION GENETIC DIVERSITY ASSESSED IN TEPHROSIA CALOPHYLLA BEDD., A RARE MEDICINAL PLANT USING RAPD MARKERS. T. P. SASIKALA; S. VENKATESWARA RAO; J. KAMAKSHAMMA // International Journal of Pharma & Bio Sciences;Jul-Sep2013, Vol. 4 Issue 3, pB-1125

Tephrosia calophylla is a perennial under-shrub with a tuberous root and is known for its various therapeutic properties. Genetic diversity was analysed using RAPD primers among 10 accessions collected from the population of Talakona, Andhra Pradesh, India. Twenty random primers , each with 10...

• Are residual economic relationships normally distributed? Testing an assumption of neoclassical economics. Bundt, Thomas; Murphy, Robert // Review of Austrian Economics;Dec2008, Vol. 21 Issue 4, p329

In both theoretical and applied contexts, neoclassical economics typically assumes that residual economic relationships are mean-zero, finite-variance, normally distributed random variables. However, many have challenged this view, from various perspectives. The Austrian economists, specifically...

• Moment inequality and complete convergence of moving average processes under asymptotically linear negative quadrant dependence assumptions. Cai, Guang-hui; Wu, Hang // Stochastic Environmental Research & Risk Assessment;Jan2006, Vol. 20 Issue 1/2, p1

Let { Y, Y i , âˆ’âˆž < i < âˆž} be a doubly infinite sequence of identically distributed and asymptotically linear negative quadrant dependence random variables, { a i , âˆ’âˆž < i < âˆž} an absolutely summable sequence of real numbers. We are inspired by Wang et al....

• The distribution of the maximum of a first order moving average: the continuous case. Withers, Christopher; Nadarajah, Saralees // Extremes;Mar2014, Vol. 17 Issue 1, p1

We give the cumulative distribution function of \$M_n\$, the maximum of a sequence of n observations from a first order moving average. Solutions are first given in terms of repeated integrals and then for the case, where the underlying independent random variables have an absolutely continuous...

Share