Assessing the statistical effectiveness of ecological experiments: utility of the coefficient of variation

The coefficient of variation (C.V.) is a statistic often used to assess the effectiveness of ecological experiments. Characteristics of C.V. behavior over time are illustrated with examples of a chemical variable (pH) and species density measurements. The ratio s/|x_i — x_j| is introduced, and a “quick‐and‐dirty” rule for a two‐sample t‐test is illustrated with data from microcosm experiments. Relationships among the C.V., minimum detectable distances between means, and statistical power of a test of hypothesis are discussed. Tabular and graphical results are presented for selected small sample sizes. Several examples with data from microcosm experiments are also given. The utility of the C.V. is considerably enhanced by the use of these statistical relationships.