Measures of dispersion

While measures of central tendency try to give an idea about where data is centered, measures of dispersion are meant to give a general idea about how data is distributed around the center. Standard deviation and variance are the most popular measures of dispersion. The square root of the variance equals the standard deviation. It's very easy to get both values with R:

sd(big_sample, na.rm = T)
# outputs [1] 5.01836
var(big_sample, na.rm = T)
# outputs [1] 25.18394

The sd() function estimates the standard deviation while var() estimates the variation. In most cases, we find ourselves with a DataFrame full of variables we want to analyze. One way out of this is to use a function that will quickly summarize the whole dataset. These functions usually work equally well both with vectors and DataFrame objects. The next section introduces a couple of them.