On Sun, Dec 27, 2020 at 3:23 AM John Darrington <j...@darrington.wattle.id.au> wrote: > > On Sat, Dec 26, 2020 at 07:58:40PM -0600, Alan Mead wrote: > Alternatively, I wouldn't be upset if PSPP refuses to print any p-value > for N < 30. I think ideally we would add a keyword requesting a more > advanced algorithm. > > I think this is probably the best course of action at least in the short > term.
If not printing a p-value for this case is likely to confuse others, perhaps the procedure should add a footnote indicating why the p-value is not output.
