At 08:29 AM 12/1/01 -0500, Stan Brown wrote:
>How I would analyze this claim is that, when the advertiser says >"90% of people will be helped", that means 90% or more. Surely if we >did a large controlled study and found 93% were helped, we would not >turn around and say the advertiser was wrong! But I think that's >what would happen with a two-tailed test. > >Can you explain a bit further? would the advertiser feel he/she was wrong if the 90% value was a little less too ... within some margin of error from 90? probably not perhaps you want to say that the advertiser is claiming around 90% or MORE, or at LEAST 90% ... again ... we are getting far too hung up in how some hypothesis is stated ... is not the more important matter ... what sort of impact is there? if that is the case ... testing a null ... ANY null ... is really not going to help you you need to look at the SAMPLE data ... then ask yourself ... what sort of a real effect might there be if i got the sample results that i did? if you then want to superimpose on this a question ... i wonder if 90 or more could have been the truth ... fine but that is an after thought this does not call for a hypothesis test >-- >Stan Brown, Oak Road Systems, Cortland County, New York, USA > http://oakroadsystems.com >My reply address is correct as is. The courtesy of providing a correct >reply address is more important to me than time spent deleting spam. > > >================================================================= >Instructions for joining and leaving this list and remarks about >the problem of INAPPROPRIATE MESSAGES are available at > http://jse.stat.ncsu.edu/ >================================================================= _________________________________________________________ dennis roberts, educational psychology, penn state university 208 cedar, AC 8148632401, mailto:[EMAIL PROTECTED] http://roberts.ed.psu.edu/users/droberts/drober~1.htm ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================
