Bayesian One sample t-test gives NaN for error%
Bayesian One sample t-test gives NaN for error% when I do it One-sided (i.e., bigger than > 0) but it gives an error when I do two-sided. Why?
Best regards
Ester
One-sided (>0) Bayesian One Sample T-Test: d BF₊₀ = 2485, error % NaN
Two-sided Bayesian One Sample T-Test: d BF₁₀ = 1242, error % 5.005e -6
Comments
Hi Ester,
The one-sided BF is calculated by departing from the two-sided BF and then adding a correcting factor. The correction factor is close to its maximum value, which might produce the problem. I'll bring it to the addition of the programming team on GitHub.
Cheers,
E.J.
Thanks, that is what I suspected. I guess I can write error approx to 0, for the moment.
The error is so small that I would not even report it.
E.J.