Abstract
We describe possibilities how the well-known linkage techniques for hierarchical clustering can be modified to consider the problem of missing values in dissimilarity data. The resulting MVL (Missing Values Linkage) approach is presented and compared with a least squares-based penalty algorithm. In an example, a distance table of selected European cities is used to demonstrate features of the MVL approach. Randomly chosen distances are assumed missing, the non-missing distances are superimposed with random error, and different subsets of cities are taken into consideration.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
ARABIE, P., and CAROLL, J.D. (1980), Mapclus: A Mathematical Approach to Fitting the ADCLUS Model, Psychometrika, 45, 211–235.
BROSSIER, G. (1990), Piecewise Hierarchical Clustering, Journal of Classification, 7, 197–216.
CAROLL, J.D., and ARABIE, P. (1983), INDCLUS: An Individual Differences Generalization of the ADCLUS Model and the MAPCLUS Algorithm, Psychometrika, 48, 157–169.
DEGENS, P.O. (1988), Reconstruction of Phylogenies by Weighted Genetic Distances, in: Classification and Related Methods of Data Analysis, ed. H.H. BOCK, North-Holland, 727–739.
De SOETE, G. (1984a), Ultrametric Tree Representations of Incomplete Dissimilarity Data, Journal of Classification, 1, 235–242.
De SOETE, G. (1984b), Additive Tree Representations of Incomplete Dissimilarity Data, Quality and Quantity, 18, 387–393.
ESPEJO, E., and GAUL, W. (1986), Two-Mode Hierarchical Clustering as an Instrument for Marketing Research, in: Classification as a Tool of Research, eds. W. GAUL and M. SCHADER, North-Holland, 121–128.
GAUL, W., and HARTUNG, J. (1979), A Barrier Method with Arbitrary Starting Point, Mathematische Operationsforschung und Statistik, Ser. Optimization, 10, 317–323.
GAUL, W., and SCHADER, M. (1988), Clusterwise Aggregation of Relations, Aplplied Stochastic Models and Data Analysis, 4, 273–282.
GAUL, W., and SCHADER, M. (1991), Pyramidal Classification Based on Incomplete Dissimilarity Data, Working Paper, submitted.
GAUL, W., SCHADER, M., and BOTH, M. (1990), Knowledge-Oriented Support for Data Analysis Applications to Marketing, in: Knowledge, Data and Computer-Assisted Decisions, eds. M. Schader and W. Gaul Springer, 259–271.
MACCALLUM, R.C. (1978), Recovery of Structure in Incomplete Data by ALSCAL, Psychometrika, 44, 69–74.
SCHADER, M., and GAUL, W. (1990), Pyramidal Clustering with Missing Values, to appear in: Proceedings INRIA Conference Symbolic — Numeric Data Analysis and Learning, Nova Science.
SCHNELL, R., and ESSER, H. (1985), Zur Effizienz einiger Missing-Data-Techniken — Ergebnisse einer Computer-Simulation, ZUMA-Nachrichten (Nov 1985), 17, 50–74.
WISHART, D. (1978), Treatment of Missing Values in Cluster Analysis, COMPSTAT 1978 Proceedings, Physica, 281–287.
WISHART, D. (1985), Estimation of Missing Values and Diagnosis Using Hierarchical Classifications, Computational Statistics Quarterly, 2, 125–134.
WISHART, D. (1986), Hierarchical Cluster Analysis with Messy Data, in: Classification as a Tool of Research, eds. W. Gaul and M. Schader, North-Holland, 453–460.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin · Heidelberg
About this paper
Cite this paper
Schader, M., Gaul, W. (1992). The MVL (Missing Values Linkage) Approach for Hierarchical Classification when Data are Incomplete. In: Schader, M. (eds) Analyzing and Modeling Data and Knowledge. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-46757-8_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-46757-8_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54708-2
Online ISBN: 978-3-642-46757-8
eBook Packages: Springer Book Archive