Almasri, Abdullah () (Centre for Labour Market Policy Research (CAFO)) Shukur, Ghazi () (Centre for Labour Market Policy Research (CAFO))
Abstract
This paper introduces and describes an alternative clustering approach based on the discrete wavelet transform (DWT) which satisfies requirements that other clustering methods, like discriminative-based clustering and model-based clustering approaches, do not satisfy. The clustering method has been constructed using wavelet analysis that has the ability of decomposing a data set into different scales. Wavelet algorithm is then used to specify the number of the clusters and quality of the clustering results at each scale. The same algorithm can be generalised for more than one-dimensional data. Some examples about how to use this approach are presented in the paper using different sample sizes and where different kinds of noises are imposed on simulated data. These examples show the successfulness and efficiency of this kind of methodology in detecting clusters under different situations.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
page. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.
Publisher Info
Paper provided by Centre for Labour Market Policy Research (CAFO), School of Management and Economics, Växjö University in its series CAFO Working Papers with number
2006:3.
Find related papers by JEL classification: C22 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Time-Series Models; Dynamic Quantile Regressions
References listed on IDEAS Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
Did you know? All full texts are decentralized with the publishers, none reside on this server, thus making it possible to offer this service for free to all parties.