Comparing dissimilarity frequency distributions and dendrograms of cluster analysis in case of plant variety description matrices

Harangozó, T. and Veress, Z. (2012) Comparing dissimilarity frequency distributions and dendrograms of cluster analysis in case of plant variety description matrices. Cereal Research Communications, 40 (1). pp. 107-115. ISSN 0133-3720

Text crc.40.2012.1.12.pdf Restricted to Repository staff only until 31 March 2032. Download (382kB)

Abstract

Plant variety descriptions are based on standardized data of morphological characteristics. Intervarietal similarity was calculated by pairwise comparison. Random numbers of 1–9 range were used in the study in order to model clear similarity relations. Similarity groups were defined shorter intervals of random numbers. Dissimilarity values were used for constructing dendrograms and dissimilarity frequency distribution (DFD) curves. DFD curve patterns and dendrograms obtained in cluster analysis were compared on eight model matrices. Dendrograms clearly separated pre-defined similarity groups but created clusters from uncorrelated random number matrices as well. DFD patterns proved to be suitable to detect similarity. The number and shape of peaks and their x axis position provided information on data set variability and similarity relations. DFD patterns clearly indicated the merging process of increased overlap of similarity groups. The new method can complement traditional cluster analysis in evaluation similarity.

Actions (login required)

Edit Item