I'm just curious if you WANT to increase chances of getting some contrasts significant "at the .05 level." If you are doing just a few select comparisons, I believe the Fisher's LSD test has more power. It's simply a t test but uses Mean Square Error in place of the pooled variance estimate, and the error df will be equal to the within error from the ANOVA. The LSD has a comparison-wide alpha level (I believe HSD has an experiment wide alpha level).
BUT, I totally agree with David - don't let a .06 or .07 stop you from looking at the data and interpreting! Most readers of what you write are far more interested in hearing about the research, what you found, what your theories/hypotheses/hunches are, that the EXACT value of p. Besides, the p is only to be trusted when all the assumptions of the test are met .... And that doesn't happen all the time. ----------------------------- John W. Kulig Professor of Psychology Director, Psychology Honors Plymouth State University Plymouth NH 03264 ----------------------------- -----Original Message----- From: David Epstein [mailto:[EMAIL PROTECTED] Sent: Tuesday, April 03, 2007 3:43 PM To: Teaching in the Psychological Sciences (TIPS) Subject: [tips] Re: ANOVA interpretation On Tue, 3 Apr 2007, Rick Froman went: > How would you interpret an ANOVA result where the F-test was > significant but none of the multiple comparisons were significant in > an HSD comparison? Initially, I wrote a response as follows: "Off the top of my head, I would say: An overall effect was detected, but the sample sizes within individual cells were not sufficiently large to attribute the effect to any specific pairwise comparison. "Then I would talk, with due caution, about what it LOOKED like." Then I did a Google search and found an explanation that's more abstruse, but still seems to invoke the problem of small sample sizes: <http://www.ats.ucla.edu/STAT/spss/library/manglm.htm> (scroll down to the section "My tests don't agree!"). Note that the explanation does *not* seem to be that you're missing "some more complicated contrast among the means." --David Epstein [EMAIL PROTECTED] --- To make changes to your subscription go to: http://acsun.frostburg.edu/cgi-bin/lyris.pl?enter=tips&text_mode=0&lang=engl ish --- To make changes to your subscription go to: http://acsun.frostburg.edu/cgi-bin/lyris.pl?enter=tips&text_mode=0&lang=english
