On Fri, Mar 5, 2010 at 12:41 PM, Jeff Laake <jeff.la...@noaa.gov> wrote:
> On 3/5/2010 9:19 AM, Frank E Harrell Jr wrote:
>
>> You neglected to state your name and affiliation, and your question
>> demonstrates an allergy to R documentation.
>
>
A:B indicates a two-level naming scheme. The naming is identical in any of
the formulas
~ A:B
~ A + A:B
~ A + B + A:B
The degrees of freedom associated with A:B depends on what other terms are
in the model.
The number of dummy variables that are retained matches the number of
degrees of freedom.
Any dummy variables that are linearly dependent on the dummy variables for
the earlier terms
are suppressed.
Please read a good intermediate statistics book for the full story.
Rich
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
