Variation is essential for natural selection in evolution. Attempts to quantify biological variation in the nineteenth century focused on its resemblance to distributions of measurement error in astronomy and physics, but in biology variable populations evolve from variable populations: the expectation is not an average with error, but a full distribution of variation in each successive generation. The normality of biological variation is geometric rather than arithmetic: biological variation is lognormal rather normal, and individual differences are differences of proportion. Logarithms employed to transform counts to proportions can be chosen to reflect halving and doubling (log2), standardized deviations (ln or loge), or orders of magnitude (log10). Comparisons of populations in standard deviation units incorporate dimension and remove its effect, making standard deviations the preferred units for expressing the similarities and differences of variable populations.