I have some distributions which are only reported by their geometric mean, geometric standard deviation, and their sample size n (all output by closed box scientific software) - is it possible to use this information alone to do a statistical test like a t-test like in the way you can with the arithmetic mean / stdev / n for each distribution?


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.