Re: [Gretl-users] Behrens-Fisher problem

Thanks Allin; ok, let's see if I understood your replies correctly: 1. The stand. dev. formula that is used in the 2-means test depends on whether both samples are large (n>30) or not. 2. If one of the samples is "small", then a formula is used that appears to be valid only in the case of equal variances. 3. there is no known/accepted way to test an arbitrary difference of means in small samples with unequal (and unknown) variances Provided those assessments are correct, I would suggest the following: ad 1) I would like to see some mention of which assumption/formula is used in the test output, or make it a user option. ad 2) This is unfortunate given that the user explicitly choose the option "do not assume equal variances". The easiest workaround is to use the asymptotic formula instead and print a warning in the output that the approximation may be poor due to the sample size. ad 3) Given that insight, I think gretl should always use asymptotic formulae for unequal variances and merely warn the user if samples are small. Ok, I expect that there are some details where I misunderstood Allin and then some of these comments would probably be off mark. Please take that into account. I just discovered the test statistic calculator and I really like it, especially for teaching. So I would like to make sure it's transparent to the user what it does. (and hopefully does the right thing) Thanks, Sven Allin Cottrell schrieb: