Is it possible for results to fluctuate a little bit even if I set set.seed? Kindly comment on the degree of freedom allowed or the possible standard deviation from the result set if seeds are fixed?

I set seeds in R and I get slightly varied results ranging from 0.1 to 0.5 S.D from previous runs. I want to know if it is normal

  • $\begingroup$ Can you show your “reproducible” code? $\endgroup$ – Blaszard Aug 13 '17 at 6:33
  • 2
    $\begingroup$ If nothing else changes, then your results should be the same if you set a seed, unless some part of your analysis, after the seed is set, involves random sampling. $\endgroup$ – bethanyP Aug 14 '17 at 2:52

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.