on 08-15-2016 03:26 PM - edited on 07-27-2021 11:37 PM by APIUserOpsDM
How can you calculate the standard deviation of the population (SDpop) rather than standard deviation on the sample data (SDsample)?
Please find the attached macro, special thanks to one of our Community users!
Standard deviation of the population (SDpop) and standard deviation on the sample (SDsample) are very similar - the only difference is that in SDpop the sum of the squared variances is divided by n instead of n-1 as it is for SD sample (where n is the number of data points in the vector). This macro takes a vector of doubles which needs to be named 'dataVals' and it returns the standard deviation of the population. Accurate out to the 9th or 10th place.
How could I alter this macro so that it can take multiple columns of data and then have it calculate a SD for each column? I'm not very good with macros and I can't figure this out.
Just I want to leave a simple solution my colleague gave me about this.
Use Summarize tool to calculate
Variance
and
CountNonNull of sample
then put formula tool to calculate
sqrt([Variance] * ([CountNonNull] - 1) / [CountNonNull])
(Which is "=STDEV.P()" in excel)