Re: [R] lme() F-values disagree with aov()

From: Peter Dalgaard <p.dalgaard_at_biostat.ku.dk>
Date: Tue 15 Aug 2006 - 01:40:14 EST

"William Simpson" <wsimpson@utsc.utoronto.ca> writes:

> > Your lme statement is OK. To get the usual split-plot anova, your aov
> > statement should be
> >
> > fit2 <- aov(y ~ a*b*c + Error(s), data = d)
>
> No, this gives wrong F-values. By "wrong" I mean it does not agree with the
> published table.

Well, it's the model that is equivalent to your lme() model....

Thing is that you want to add random effects of s:b and s:c, which are crossed factors, so somewhat tricky to code with lme() (this sort of thing is easier in lmer() from the lme4 packages).

The generic way to handle this in lme() is via something like

           random=list(s=pdBlocked(list(
                     pdIdent(~1),
                     pdIdent(~b-1),
                     pdIdent(~c-1))))

You probably won't get the degrees of freedom right, though.  

> Table 12.10-2, page 559:
> Number of obs = 32 R-squared = 0.9920
> Root MSE = .559017 Adj R-squared = 0.9589
>
> Source | Partial SS df MS F Prob > F
> -----------+----------------------------------------------------
> Model | 233.625 25 9.345 29.90 0.0002
> |
> a | 3.125 1 3.125 2.00 0.2070
> s|a | 9.375 6 1.5625
> -----------+----------------------------------------------------
> b | 162.00 1 162.00 199.38 0.0000
> a*b | 6.125 1 6.125 7.54 0.0335
> b*s|a | 4.875 6 .8125
> -----------+----------------------------------------------------
> c | 24.50 1 24.50 61.89 0.0002
> a*c | 10.125 1 10.125 25.58 0.0023
> c*s|a | 2.375 6 .395833333
> -----------+----------------------------------------------------
> b*c | 8.00 1 8.00 25.60 0.0023
> a*b*c | 3.125 1 3.125 10.00 0.0195
> |
> Residual | 1.875 6 .3125
> -----------+----------------------------------------------------
> Total | 235.50 31 7.59677419
>
> Bill
>
> ______________________________________________
> R-help@stat.math.ethz.ch 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.
>

-- 
   O__  ---- Peter Dalgaard             ěster Farimagsgade 5, Entr.B
  c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
 (*) \(*) -- University of Copenhagen   Denmark          Ph:  (+45) 35327918
~~~~~~~~~~ - (p.dalgaard@biostat.ku.dk)                  FAX: (+45) 35327907

______________________________________________
R-help@stat.math.ethz.ch 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.
Received on Tue Aug 15 01:42:47 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Tue 15 Aug 2006 - 02:23:43 EST.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.