Data of measurements of ten individual plants height, from ten randomized blocks design experiments, with four replications and four cotton cultivars, were evaluated to determine the minimum number of plants per plot for characterization of the average height in cotton. To reach the purpose of this work, five sample sizes in the plot were studied, with 2, 4, 6, 8 and 10 plants each. The coefficients of experimental and amostral variation, as well as the significative analysis of variances, indicated that plots with six or more plants allowed a good characterization of the plant height. The results showed that in the characterization of the height of the gossypium plants, the evaluating become fast and it can have a reduction in the labor during the collection and handling of the data, due to the reduction of the number of plants sampled in the plot.
sampling; coefficient of variation sampling; coefficient of variation
