Agroclimatic classification; numeral-taxonomic procedures-a review

• Autor(a) principal: Reddy, S. Jeevananda
• Data de Publicação: 2014
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Pesquisa Agropecuária Brasileira (Online)
• Texto Completo: https://seer.sct.embrapa.br/index.php/pab/article/view/15263
• topic: graphical classification; ordination; cluster analysis; similarity measures; classificação gráfica; chamada de ordenação; análise de clustes; medidas semelhantes

The paper catalogues the procedures and steps involved in agroclimatic classification. These vary from conventional descriptive methods to modern computer-based numerical techniques. There are three mutually independent numerical classification techniques, namely Ordination, Cluster analysis, and Minimum spanning tree; and under each technique there are several forms of grouping techniques existing. The choice of numerical classification procedure differs with the type of data set. In the case of numerical continuous data sets with both positive and negative values, the simple and least controversial procedures are unweighted pair group method (UPGMA) and weighted pair group method (WPGMA) under clustering techniques with similarity measure obtained either from Gower metric or standardized Euclidean metric. Where the number of attributes are large, these could be reduced to fewer new attributes defined by the principal components or coordinates by ordination technique. The first few components or coordinates explain the maximum variance in the data matrix. These revised attributes are less affected by noise in the data set. It is possible to check misclassifications using minimum spanning tree.