0
$\begingroup$

Let's say we know the standard deviation of a set of data. Furthermore, that set of data can be partitioned into subsets, and we know the standard deviation for each subset of that partition. What's the relationship between those standard deviations and the one for the whole set? Is it simple, like an average, or more complicated?

$\endgroup$
2
  • $\begingroup$ Answered many times on site already. It's more complicated (it's easy to see that you can't just average them by simply taking a small example set of data, splitting it in two and computing the standard deviations of the whole and the two parts). You will also need the means and sample sizes of the subsets. $\endgroup$
    – Glen_b
    Jan 26, 2019 at 5:24
  • $\begingroup$ See here for the two-variable case: en.wikipedia.org/wiki/Pooled_variance#Sample-based_statistics $\endgroup$
    – Glen_b
    Jan 26, 2019 at 5:35

0

Browse other questions tagged or ask your own question.