Quantifying the quality of phytocoenotic classification (theoretical-methodological aspect)
DOI:
https://doi.org/10.14255/2308-9628/16.121/4Keywords:
classification of vegetation, cluster analysis, phytocoenon, classification quality indexes.Abstract
This article reviews quantitative approaches to assessing the quality of phytocoenons and phytocoenotic classification. Mathematical criterion is based on calculating phytocoenon’s compactness / distinctness ratio computed from a distance matrix between releves by species composition. Floristic criterion assumes evaluating diagnostic power of species and takes into account total amount of differential species which are classified statistically with fidelity indexes. We also considered related methods which European phytocoenologists applied for the same purpose – among them indexes of sharpness and uniqueness of syntaxon and the Optimclass approach. We measured resemblance of phytocoenotic classifications of the dataset using contingency tables and nominal correlation coefficients. We determined stability of phytocoenons and the robustness of the cluster topology using bootstrapping methods.
References
BOTTA-DUKÁT Z., CHYTRÝ M., HÁJKOVÁ P., HAVLOVÁ M. (2005). Vegetation of lowland wet meadows along a climatic continentality gradient in Central Europe. Preslia, 77: 89-111.
CHYTRÝ M., TICHÝ L. (2003). Diagnostic, constant and dominant species of vegetation classes and alliances of the Czech Republic: a statistical revision. Folia Facultatis Scientiarum Naturalium Universitatis Masarykianae Brunensis, Biologia, 108: 1-231.
CHYTRÝ M., TICHÝ L., HOLT J., BOTTA‐DUKÁT Z. (2002). Determination of diagnostic species with statistical fidelity measures. Journal of Vegetation science, 13 (1): 79-90.
CRAMÉR H. (1946). Mathematical Methods of Statistics. Princeton: Princeton University Press. 282 p.
DE CÁCERES M., FONT X., OLIVA F. (2008). Assessing diagnostic species value in large data sets: A comparison between phi-coefficient and Ochiai index. Journal of Vegetation science, 19: 779-788.
DUFRÊNE M., LEGENDRE P. (1997). Species assemblages and indicator species: the need for a flexible asymmetrical approach. Ecol. Monogr., 67: 345-366.
DUNN J.C. (1974). Well separated clusters and optimal fuzzy partitions. Journal of Cybernetics, 4: 95-104.
FOWLKES E.B., MALLOWS C.L. (1983). A method for comparing two hierarchical clusterings. Journal of the American statistical association, 78 (383): 553-569.
GOLUB V.B., SOROKIN A.N., MALTSEV M.V., CHUVASHOV A.V. (2012). Vestnik Volzhskogo universiteta im. V.N. Tatishcheva, 3: 308–317. [ГОЛУБ В.Б., СОРОКИН А.Н., МАЛЬЦЕВ М.В., ЧУВАШОВ А.В. (2012). Почвы и растительность многолетней залежи в дельте Р. Волги. Вестник Волжского университета им. В.Н. Татищева, 3: 308-317]
GOLUB V.B., STARICHKOVA K.A., BARMIN A.N., IOLIN M.M., SOROKIN A.N., NIKOLAICHUK L.F. (2013). Estimate of vegetation dynamics in the Volga delta. Arid ecosystems, 3(3): 156-164.
GONCHARENKO I.V. (2015). Vegetation of Russia. 27: 125-138. [ГОНЧАРЕНКО И.В. (2015). DRSA: алгоритм неиерархической кластеризации с использованием k-NN графа и его применение в классификации растительности. Растительность России. 27: 125-138]
GOODMAN L.A., KRUSKAL W.H. (1954). Measures of association for cross-classification. J. Am. Stat. Assoc., 49: 732-764.
HALKIDI M., BATISTAKIS Y., VAZIRGIANNIS M. (2001). On Clustering Validation Techniques. Journal of Intelligent Information Systems, 17: 107-145.
HENNIG C. (2013). fpc: Flexible Procedures For Clustering. R Package Version 2.1-6. available at: http://www.homepages.ucl.ac.uk/~ucakche/ (accessed 01 April 2016)
JACCARD P. (1901). Distribution de la flore alpine dans le Bassin des Dranses et dans quelques regions voisines. Bull. Soc. Vaudoise sci. Natur, 37 (140): 241-272.
JAROLÍMEK I., ŠIBÍK J., TICHÝ L., KLIMENT J. (2010). Sharpness and uniqueness of the phytosociological classes of Slovakia. Annali di Botanica, Nuova Serie, Roma, 10: 11-18.
MANDEL I.D. (1988). Klasternyi analiz. M.: Finansy i statistika. 176 p. [МАНДЕЛЬ И.Д. (1988). Кластерный анализ. М.: Финансы и статистика. 176 с.]
RENDÓN E., ABUNDEZ I., ARIZMENDI A., QUIROZ E. (2011). Internal versus external cluster validation indices. Int. J. Computers and Communications, 5: 27-34.
ROUSSEEUW P.J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20: 53-65.
SHITIKOV V.K. (2012). Printsipy ekologii, 1: 4-24. [ШИТИКОВ В.К. (2012). Использование рандомизации и бутстрепа при обработке результатов экологических наблюдений. Принципы экологии, 1: 4-24]
SØRENSEN T.A. (1948). A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on Danish commons. Kongelige Danske Videnskabernes Selskab. Biol. krifter, 5: 1-34.
TICHÝ L. (2002). JUICE, software for vegetation classification. Journal of vegetation science, 13 (3): 451-453.
TICHÝ L., CHYTRÝ M., HÁJEK M., TALBOT S. S., BOTTA-DUKÁT Z. (2010). OptimClass: Using species-to-cluster fidelity to determine the optimal partition in classification of ecological communities. Journal of Vegetation science, 21: 287-299.
TICHÝ L., CHYTRÝ M., SMARDA P. (2011). Evaluating the stability of the classification of community data. Ecography, 34 (5): 807-813.
WALLACE D.L. (1983). Comment. Journal of the American Statistical Association, 78 (383): 569-576.
