The median absolute deviation is the median of the distances from the median. It is one of the most robust measures of spread: up to half the data can be wild outliers without breaking it.
MAD = median(|xᵢ − median(x)|) · scaled MAD = 1.4826 × MAD
The scaled MAD estimates the standard deviation when the data are normal, which makes it useful for robust outlier rules such as “more than 3 scaled MADs from the median”.