Hey Maria,<br><br>I suspect you removed some outliers and how do not have a balanced data set anymore? As David was saying, if you do not have a balanced data set sum (aka) contrast coding does <i>not</i> center your categorical predictors. (You can center them yourself if you want to. That is probably the reason for the mismatch. If so, then the intercept-only model should give you the expected estimate <i>unless</i> the random effects are not actually summing up to zero. That actually does happen (and then they essentially contain part of what you would expect to be the intercept). It's a good idea to check the distribution of the random effects anyway.<br>
<br>Unrelated to your problem, have you tried including random slopes for the two main effects? Seems like a good idea given your data. <br><br>Finally, just out of curiosity, are you looking at whether repeated nouns between prime and target affect priming? You may find Neal Snider's work interesting in that case. He has looked at how overall prime-target similarity affects the strength of priming. (he found an effect, but his study is more general than noun identity; btw, I recall that he once told me that noun repetition alone did not reach significance).<br>
<br>Florian<br><br><div class="gmail_quote">On Wed, Apr 8, 2009 at 6:54 PM, David Reitter <span dir="ltr"><<a href="mailto:reitter@cmu.edu">reitter@cmu.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hi Maria,<br>
<br>
good to hear from you. Just briefly for lack of time:<div class="im"><br>
<br>
On Apr 7, 2009, at 5:28 AM, Maria Carminati wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Generalized linear mixed model fit using Laplace<br>
Formula: poresp ~ primec * nounrepc + (1 | subject) + (1 | item)<br>
Data: verbdiff<br>
</blockquote>
<br>
</div><div class="im"><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
THERE WERE OVERALL 872 SUCCESSES AND 302 FAILURES IN THE EXPT, SO ODDS<br>
SHOULD BE 872/302=2.88 or (in probability space) .74/.26 = 2.85;<br>
THIS SHOULD GIVE A LOG OF ODDS OF APPROX 1.05, BUT THE INTERCEPT<br>
PREDICTED BY THE MODEL IS MUCH HIGHER (1.66)<br>
</blockquote>
<br></div>
You have a random intercept for subjects (and one for items) fitted there...<br>
I would fit a fixed effects model and check that first. I'm not sure if, given the groups defined for your random terms, all data points are weighted equally (as they are in your max likelihood probability above).<br>
(Finally, by coding your binary factors as -0.5,0.5, you don't necessarily center the means at 0 - unless your design is balanced, what I almost suspect. If their means aren't 0, you wouldn't expect the fitted intercept to work out the way you're suggesting.)<br>
<br>
Also, what happens if you take the non-significant terms out?<div class="im"><br>
<br>
> primec:nounrepc -0.2138 0.3224 -0.663 0.507<br>
<br></div>
Pity this one didn't work. Where these low-frequency nouns? Unless your design controlled their frequency, you could try adding terms for the noun log-frequency (from a corpus)...<br>
<br>
<br>
Best<br>
- David<br><font color="#888888">
<br>
--<br>
Dr. David Reitter<br>
Department of Psychology<br>
Carnegie Mellon University<br>
<a href="http://www.david-reitter.com" target="_blank">http://www.david-reitter.com</a><br>
<br>
</font><br>_______________________________________________<br>
R-lang mailing list<br>
<a href="mailto:R-lang@ling.ucsd.edu">R-lang@ling.ucsd.edu</a><br>
<a href="http://pidgin.ucsd.edu/mailman/listinfo/r-lang" target="_blank">http://pidgin.ucsd.edu/mailman/listinfo/r-lang</a><br>
<br></blockquote></div><br>