An examination of indexes for determining the number of clusters in binary data sets

Dimitriadou, Evgenia; Dolničar, Sara; Weingessel, Andreas

doi:10.1007/bf02294713

Cited by 234 publications

(157 citation statements)

References 31 publications

Supporting

Mentioning

140

Contrasting

Order By: Relevance

“…The measures are of different types in that they examine different aspects of the clusters and were found superior to other existing measures in studies aimed to find the best measures. (See Milligan &Cooper, 1985, andDimitriadou, Dolnicar, &Weingessel, 2002, for detailed descriptions of these measures.) Some of these measures (such as the CCC and the Calinski and Harabasz measure) are maximized for the optimum number of clusters; some others (such as the Davies and Bouldin measure) are minimized for the optimum number of clusters.…”

Section: Model 4: Test For Equal Factor Variances and Covariances Thmentioning

confidence: 99%

INVESTIGATING THE VALUE OF SECTION SCORES FOR THE TOEFL iBT® TEST

Sawaki

Sinharay

2013

ETS Research Report Series

View full text Add to dashboard Cite

This study investigates the value of reporting the reading, listening, speaking, and writing section scores for the TOEFL iBT ® test, focusing on 4 related aspects of the psychometric quality of the TOEFL iBT section scores: reliability of the section scores, dimensionality of the test, presence of distinct score profiles, and the section scores' generalizability for norm-referenced decisions as well as the dependability of criterion-referenced decisions for international student admission.Four operational TOEFL iBT test forms were analyzed for all examinees as well as for 3 native language (L1) groups (Arabic, Korean, and Spanish).Haberman's (2008) subscore analysis suggested that the speaking section score had added value due to its relative distinctness from the other modalities. Consistent with the subscore analysis results, a series of exploratory factor analyses (EFAs) indicated the possibility of the presence of 2 correlated factors-a reading/listening/writing factor and a speaking factor.In contrast, the CFAs conducted separately for the 3 L1 groups as well as a multiple-group confirmatory factor analyses (CFAs) identified a correlated 4-factor model with reading, listening, speaking, and writing factors as the best representation of the structure of the entire test for all examinees as well as for the 3 L1 groups. Reliability of the observed section scores for norm-referenced score interpretations and the dependability of classification decisions made based on different cut scores were generally satisfactory while they were also found to be relatively low in some circumstances. Based on the mixed results concerning the value-added information the TOEFL iBT section scores provide, recommendations for future research directions and some key issues of consideration for high-stakes decision making based on the section scores were summarized.Key words: dependability, dimensionality, factor analysis, generalizability theory, reliability, score profile, subscore analysis ii TOEFL ® was developed in 1963 by the National Council on the Testing of English as a Foreign Language. The Council was formed through the cooperative effort of more than 30 public and private organizations concerned with testing the English proficiency of nonnative speakers of the language applying for admission to institutions in the United States. In 1965, Educational Testing Service (ETS) and the College Board ® assumed joint responsibility for the program. In 1973, a cooperative arrangement for the operation of the program was entered into by ETS, the College Board, and the Graduate Record Examinations ® (GRE ® ) Board. The membership of the College Board is composed of schools, colleges, school systems, and educational associations; GRE Board members are associated with graduate education. The test is now wholly owned and operated by ETS.ETS administers the TOEFL program under the general direction of a policy board that was established by, and is affiliated with, the sponsoring organizations. Members of the TOEFL Board (previo...

show abstract

Section: Model 4: Test For Equal Factor Variances and Covariances Thmentioning

confidence: 99%

INVESTIGATING THE VALUE OF SECTION SCORES FOR THE TOEFL iBT® TEST

Sawaki

Sinharay

2013

ETS Research Report Series

View full text Add to dashboard Cite

show abstract

“…This question is similar to the typical "number of clusters" question (Thorndike, 1953). A huge number of indices has been proposed in the literature for assessing the number of clusters (see, e.g., Milligan and Cooper, 1985;Dimitriadou et al, 2002). For model-based clustering information criteria like the AIC or BIC can be used (e.g., Fraley and Raftery, 1998).…”

Section: The Benchmarking Frameworkmentioning

confidence: 98%

Evaluation of structure and reproducibility of cluster solutions using the bootstrap

2009

View full text Add to dashboard Cite

Segmentation results derived using cluster analysis depend on (1) the structure of the data and (2) algorithm parameters. Typically neither the data structure is assessed in advance of clustering nor is the sensitivity of the analysis to changes in algorithm parameters. We propose a benchmarking framework based on bootstrapping techniques that accounts for sample and algorithm randomness. This provides much needed guidance both to data analysts and users of clustering solutions regarding the choice of the final clusters from computations which are exploratory in nature. This is a preprint of an article that has been accepted for publication in Marketing Letters. The original publication is available at www.springerlink.com. Please use the journal version for citation, see http://dx.doi.org/10.1007/s11002-009-9083-4 for details. Disciplines Business | Social and Behavioral Sciences AbstractSegmentation results derived using cluster analysis depend on (1) the structure of the data and (2) algorithm parameters. Typically neither the data structure is assessed in advance of clustering nor is the sensitivity of the analysis to changes in algorithm parameters. We propose a benchmarking framework based on bootstrapping techniques that accounts for sample and algorithm randomness. This provides much needed guidance both to data analysts and users of clustering solutions regarding the choice of the final clusters from computations which are exploratory in nature.

show abstract

“…The prediction of number of clusters was improved by a weighted voting technique. The number of clusters in artificial datasets was examined by Dimitriadou et al [24] using 14 cluster validation indices. A new method to estimate number of clusters in the dataset was developed by Dudoit et al [25].…”

Section: Related Workmentioning

confidence: 99%

Vinayaka : A Semi-Supervised Projected Clustering Method Using Differential Evolution

Gajawada¹

2012

IJSEA

View full text Add to dashboard Cite

show abstract

An examination of indexes for determining the number of clusters in binary data sets

Abstract: number of clusters, clustering indexes, binary data, artificial data sets, market segmentation,

Cited by 234 publications

References 31 publications

INVESTIGATING THE VALUE OF SECTION SCORES FOR THE TOEFL iBT® TEST

INVESTIGATING THE VALUE OF SECTION SCORES FOR THE TOEFL iBT® TEST

Evaluation of structure and reproducibility of cluster solutions using the bootstrap

Vinayaka : A Semi-Supervised Projected Clustering Method Using Differential Evolution

Contact Info

Product

Resources

About