R help - Apr 2006 - New behavior in estimable(), bug or feature?

Hello all!

w2k, R-2.2.1. "update.packages" done today.

I just started to work with a new dataset, using lme() (library nlme) and
estimable() (library gmodels). I first wanted to establish the fixed
effects for eight fertiliser treatments (variable treat) coded as A to H.

Fitting and reducing a first model for grain yield went smoothly. When I
wanted to look at the fixed effects with estimable() I got an error
message claiming that I was using the wrong variable names, estimable
wanted the variable names in the form usually given by fixed.effects().

I changed the names in my matrix to the requested form, but got the same
error message. Then I changed to an old library with a variety trial
material using a matrix I _know_ worked two months ago, I got the same
type of error message.

What is happening?
Is there a new namecheck in estimable acting a little over-enthusiastic or
what?

Here are some output from R:
> trMat1
A 1 0 0 0 0 0 0 0
B 0 1 0 0 0 0 0 0
C 0 0 1 0 0 0 0 0
D 0 0 0 1 0 0 0 0
E 0 0 0 0 1 0 0 0
F 0 0 0 0 0 1 0 0
G 0 0 0 0 0 0 1 0
H 0 0 0 0 0 0 0 1
> formula(m4.y)
y.dm ~ treat - 1
> fixed.effects(m4.y)
  treatA   treatB   treatC   treatD   treatE   treatF   treatG   treatH
2065.267 4052.033 4571.479 4933.026 4680.980 5021.347 5063.306
5198.153
> estimable(m4.y, trMat1)
Error in FUN(newX[, i], ...) :
        Invalid parameter name(s): , , , , , , ,
        Valid names are: treatA, treatB, treatC, treatD, treatE, treatF,
treatG, treatH
>

All the best
/CG

-- 
CG Pettersson, MSci, PhD Stud.
Swedish University of Agricultural Sciences (SLU)
Dep. of Crop Production Ekology. Box 7043.
SE-750 07 Uppsala, Sweden
cg.pettersson at vpe.slu.se

CG Pettersson <cg.pettersson <at> evp.slu.se> writes:
> 
> 
> Fitting and reducing a first model for grain yield went smoothly. When I
> wanted to look at the fixed effects with estimable() I got an error
> message claiming that I was using the wrong variable names, estimable
> wanted the variable names in the form usually given by fixed.effects().
... 
> What is happening?
> Is there a new namecheck in estimable acting a little over-enthusiastic or
> what?
> 
Yes, estimable has change that it accepts parameter NAMES now, and this might 
collide with some implicit typecasting:

Docs:
"If cm is a vector, it should contained named elements each of which gives
the
coefficient to be applied to the corresponding parameter. "

Since you did not provide a runnable example, I cannot check in detail what was 
wrong.

Dieter