Thanks for your response; with so little information you clearly
understand what I’m trying to do. However I think now that I
need to do a subsequent analysis after ANOVA. All my results were
significant. I think I want to do a kind of multiple comparison to see
which level of the independent variables had the greatest effect. Am I
along the right track and if so how do I apply this using SPSS. I hope
you don’t mind but I emailed you my interpretation of the
results and would really appreciate it if you could advise me further.
Thanks again

George









[EMAIL PROTECTED] (JJ Diamond) wrote in message 
news:<[EMAIL PROTECTED]>...
> [EMAIL PROTECTED] (George Caine) wrote in message 
>news:<[EMAIL PROTECTED]>...
> > I am completing my results section for my dissertaion and have decided
> > to use a 2by3 analysis of variance. I know this is the most effective
> > test statistic to apply to my study. However, I am worried that my
> > result section may be too short and feel it doesnt allow me to
> > demonstrate as much statistical knowledge as I would like. Is there
> > any subsequent analysis I could apply or does it matter?? any advice
> > would be greatly appreciated.
> > George Caine
> 
> well George - there might be some things to do, so to speak, depending
> on other things.  since you said nada about the study and the
> variables, it is a bit hard to comment.  but you may have a large sums
> of squares for interaction that would be of interest.  you have 2
> degrees of freedom for the three-level factor.  is this a quantitative
> variable with equal injtervals like practrice time of 10 or 20 or 30
> minutes, or something like that?  if so, you can do some fun trend
> analyses of linear and quadratic trends.  failing this, you can, given
> a significant three-level effect and no significant interaction run
> some kind of a post hoc test like scheffe'.  overall it sounds like
> you could use a consultant.  is that kosher for a dissertation or
> should the candidate know what's going on statistically.  i guess
> that's for you and your chairman to decide!
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to