Sample size and sampling method for evaluation of characteristics of the sunflower

Resumo

In the sunflower, in addition to seed yield, it is of interest to evaluate number of leaves plant-1, head diameter, stem diameter and plant height, since these characteristics may be associated with seed yield  or lodging. The objective of the work was to determine the optimal sample size (from which the experimental coefficient of variation, CV, can be established) for evaluation of these four characteristics. Fifteen cultivars were evaluated in an experimental design of randomized blocks with ten replications. The characteristics were evaluated using two sampling methods (in a single row of plants or in the two rows from the useable area of each plot) and sample sizes of from two to 18 sampling units, with an interval of two plants. In the two sampling methods, the experimental accuracy, as measured by the CV, increased with increasing sample size. A sample made up of ten sampling units is suitable for assessing the number of leaves, the diameters of the head and stem, and the plant height in cultivars of the sunflower. From this sample size upwards, additional gains in experimental precision are not obtained. This sample size can be used to evaluate plants in a single row or in two rows taken from the useable area of each plot, since there was virtually no difference between sampling methods with regard to experimental accuracy. However, it is most practical and quick to sample in one row of plants.