You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I believe it would be a great addition to the package!
Generally, when reporting GG corrected p-values, the corrected F value and ddofs are also reported.
It is also a relatively easy addition.
(...) if correction:
(...) corr_fval = f(corr_ddof1, corr_ddof2).ppf(1-p_corr)
then during the formation of dataframe:
if not detailed:
(....) aov["F"] = corr_fval aov["DF"] = [corr_ddof1,corr_ddof2]
else:
(...) aov["DF"] = [corr_ddof1,corr_ddof2] aov["F"] = [corr_fval,np.nan]
(...)
The text was updated successfully, but these errors were encountered:
I don't think we should replace the F-value and DF, because we are still reporting the uncorrected p-value. If anything, we should add the F_corr and DF_corr to the dataframe, but I am worried that it will overburden the output, which is already quite extensive.
Alternatively, we could switch to a class implementation class RepeatedMeasuresANOVA where there would be methods to report the corrected and non-corrected values. I've been wanting to rewrite some of these functions using https://github.com/matthewwardrop/formulaic as the backend, but this will take a significant amount of time which I don't have now.
I believe it would be a great addition to the package!
Generally, when reporting GG corrected p-values, the corrected F value and ddofs are also reported.
It is also a relatively easy addition.
(...)
if correction:
(...)
corr_fval = f(corr_ddof1, corr_ddof2).ppf(1-p_corr)
then during the formation of dataframe:
if not detailed:
(....)
aov["F"] = corr_fval
aov["DF"] = [corr_ddof1,corr_ddof2]
else:
(...)
aov["DF"] = [corr_ddof1,corr_ddof2]
aov["F"] = [corr_fval,np.nan]
(...)
The text was updated successfully, but these errors were encountered: