[much snippage. I've tried my best to avoid distorting anyone's position.]
Herman Rubin wrote: > > In article <[EMAIL PROTECTED]>, > Jerry Dallal <[EMAIL PROTECTED]> wrote: > >It's one thing to say that significance > >tests have to be used properly. It's another to say they should be > >abandoned. > > Where have I ever said they have to be abandoned? The > real question is whether one should act as if the null > hypothesis is close enough. If we're able to agree they have their place, then there's no disagreement. > >I might look at NEJM or JAMA and use > >significance tests to *help* me choose a treatment. > > I suggest you look a little more carefully. You would > probably use more than the significance test. Of course. That's why I said "to *help* me". I didn't say I'd use only significance tests. > > >> As it is > >> rarely possible to be sure of anything important from > >> data, what needs to be done is to balance the various > >> consequences of errors. > > >In theory, but what about in practice? Where are the scores of > >decision theoretic analyses that have exposed the harm done by > >significance tests? > > Many have appeared. I'd enjoy reading a reference or two to such real applications. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
