Hi Claire,<br><br>More generally, too, it is not surprising to find that two codings differ in collinearity (e.g. treatment coding vs. contrast/sum coding). Which coding you should use depends on (a) what hypothesis you want to test and (b) if you need to reduced collinearity (b/c you need reliable estimates of effect direction and/or effect shape, since otherwise you could simply use model comparison).<br>
<br>florian<br><br><div class="gmail_quote">On Mon, Apr 20, 2009 at 6:16 AM, Matthew Roberts <span dir="ltr"><<a href="mailto:Matthew.Roberts@ed.ac.uk">Matthew.Roberts@ed.ac.uk</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;">
Are you sure that the numeric values are the same in each case? When R<br>
converts factor() to numeric(), it take the numerical factor id rather<br>
than the name. To avoid this do:<br>
<br>
numeric.condition.number <- as.numeric(as.character(factor.condition.number))<br>
<br>
Hope this helps,<br>
<br>
Matthew<br>
<br>
* Claire Delle Luche <<a href="mailto:Claire.Delleluche@univ-lyon2.fr">Claire.Delleluche@univ-lyon2.fr</a>> [2009-04-20 10:41:58 +0200]:<br>
<div><div></div><div class="h5"><br>
> Dear R-users,<br>
><br>
> I am running a mixed effect model on a written corpus.<br>
> When I check for collinearity, I get a value of 35 for condition number when my predictors are entered as names then transformed as numeric (the values are 1 and 2 for two level predictors after the transormation).<br>
> However, when I enter the predictors as factors and assign levels of 0 and 1 instead of names (and convert them as numeric), I get a condition number of 12.<br>
><br>
> For the same data, depending on how I code the predictors, I either have moderate or important collinearity. What shall I do?<br>
> Which coding is more acceptable?<br>
><br>
> Thanks very much in advance.<br>
><br>
> Yours,<br>
><br>
> Claire Delle Luche<br>
> Laboratoire Dynamique du Langage<br>
> 14, avenue Berthelot<br>
> 69 007 Lyon<br>
> France<br>
><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>
<br>
</div></div>--<br>
Matthew A. J. Roberts<br>
Department of Psychology,<br>
University of Edinburgh,<br>
7 George Square<br>
EH8 9JZ<br>
+44 (0)131 6511302<br>
<font color="#888888">--<br>
<br>
The University of Edinburgh is a charitable body, registered in<br>
Scotland, with registration number SC005336.<br>
</font><div><div></div><div class="h5"><br>
<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>
</div></div></blockquote></div><br>