Note on the Use of Coefficient of Variation for Data from Agricultural Factorial Experiments

M. KOZAK1, J. BOCIANOWSKI2 and W. RYBINSKI3
1 Warsaw University of Life Sciences, Department of Botany, 02-766 Warsaw, Poland
2 Poznan University of Life Sciences, Department of Mathematical and Statistical Methods, 60-637 Poznan, Poland
3 Polish Academy of Science, Institute of Plant Genetics, 60-479 Poznan, Poland

Abstract

KOZAK, M., J. BOCIANOWSKI and W. RYBINSKI, 2013. Note on the use of coefficient of variation for data from agricultural factorial experiments. Bulg. J. Agric. Sci., 19: 644-646

 

Coefficient of variation is very often used to describe variability in a variable. However, when the variable is studied in a factorial experiment, it can be used to determine pooled coefficient of variation, based on the variance of the residual term from an analysis of variance model. Such a coefficient disregards the variability that comes from the sources of variation from the experiment. Because this issue is not mentioned in any of textbooks we know, this paper aims to underline such a use of coefficient of variation, and presents it for a two-year plant breeding experiment on grass pea.

Key words: analysis of variance, estimation, factorial experiments, variability

See the article as a PDF.