[R] Hierarchical Regression

Peter Dalgaard BSA p.dalgaard at biostat.ku.dk
Tue Apr 4 11:58:48 CEST 2000

Ragnar Beer <rbeer at uni-goettingen.de> writes:

> Howdy!
> I'm a clinical psychologist desperately trying to get rid of SPSS. I 
> just discovered R and like it quite a lot. The main reason why we're 
> still using SPSS  is the hierarchical regression where you enter 
> bundles of variables into a linear model and get an R-sqare increase 
> tested with an F-test. I already found add1 and drop1 but would 
> rather need addn and dropn. Is there something like that? Or how else 
> can I get what I want?
> --Ragnar

You can compare any two (nested!!) models with anova(model1,model2)
and get the F-test between them. (Currently there's no sanity check
that you're actually applying the models to the same data and have a
strict ordering of models, but this is rather high up on our TODO list
for 1.1.0)

If you're thinking in terms of model search procedures, also have a
look at step() and the leaps package.

   O__  ---- Peter Dalgaard             Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics     2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark      Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)             FAX: (+45) 35327907
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list