Originally Posted by

**abender** It is always better to use $\displaystyle \sigma$ instead of $\displaystyle s$; however, in practice you will often be given a large set of data and will only be able to compute $\displaystyle s$. When your data are large enough, you may approximate $\displaystyle \sigma$ with $\displaystyle s$.

Bottom line: Use $\displaystyle \sigma$ if you have it, but don't hesitate to use $\displaystyle s$ if your data are large as an approximation to $\displaystyle \sigma$.

I hope this clears things up for you.

Best,

Andy