[R-lang] Re: coding in unbalanced data

[T. Florian Jaeger]

Hi Bruno, Philip,

let me react to this somewhat belatedly.

First, unbalanced data in LME models will not lead to fixed effect
> correlations, certainly not with the number of data points that
> reading time studies yield. The ability of LME models to handle
> unbalanced data is one of the things that makes it so great.
>

Just to be on the safe side, I would qualify this statement a bit. For large
data sets, small deviations from balanced data are unlikely to result in
large fixed effect correlations if you use e.g. sum or Helmert coding.

To learn about coding in R, you might also find Maureen Gillespie's tutorial
useful, which is hosted on the HLP Lab blog (
http://hlplab.wordpress.com/2010/05/10/mini-womm-montreal-slides-now-available/).
It goes through different codings and provides R code so that you can follow
along and understand the consequences of the different ways of coding your
data.

Florian

>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailman.ucsd.edu/mailman/private/ling-r-lang-l/attachments/20100920/aad384d8/attachment.html