0

I have some 300K probabilities represented as logarithms. I need the average and standard deviation. Is there a better way than exponentiating and calculating the usual way? Solution preferred in Perl / Python / anything I can run from the Linux shell.

Sixtease
  • 790
  • 8
  • 18
  • You need the average and sd of the numbers of the original values, not the logged? – Reeza Dec 09 '20 at 18:01
  • @Reeza yes, exactly. – Sixtease Dec 09 '20 at 18:10
  • Just to clarify these are log with the same base, and not the estimates from logistic regression or something? – Reeza Dec 09 '20 at 18:14
  • 1
    It's easier to help you if you include a simple [reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) with sample input and desired output that can be used to test and verify possible solutions. – MrFlick Dec 09 '20 at 18:34
  • From checking the log and exp identities I don't think there's a simplification for this process :(. – Reeza Dec 09 '20 at 18:52

0 Answers0