R help - May 2007 - Design matrix question

Hi useRs,

Perhaps I am having a senior moment?

I have a nested variable situation to model,

toy example:

> df <- data.frame(A = factor(c("a", "a",
"x", "x"), levels = c("x", "a")),
+                  B = factor(c("b", "x", "x",
"x"), levels = c("x",
"b")))
> 
> df
  A B
1 a b
2 a x
3 x x
4 x x

So of course the full design matrix is singular
> model.matrix(~ A * B, df)
  (Intercept) Aa Bb Aa:Bb
1           1  1  1     1
2           1  1  0     0
3           1  0  0     0
4           1  0  0     0
attr(,"assign")
[1] 0 1 2 3
attr(,"contrasts")
attr(,"contrasts")$A
[1] "contr.treatment"

attr(,"contrasts")$B
[1] "contr.treatment"


I'd like not to have the B term main effect in the model
> model.matrix(~ A * B - B, df)
  (Intercept) Aa Ax:Bb Aa:Bb
1           1  1     0     1
2           1  1     0     0
3           1  0     0     0
4           1  0     0     0
attr(,"assign")
[1] 0 1 2 2
attr(,"contrasts")
attr(,"contrasts")$A
[1] "contr.treatment"

attr(,"contrasts")$B
[1] "contr.treatment"
> 
How do I get model.matrix to not add that
column of zeroes?

Why does model.matrix add that column of zeroes?

Is this a bug, or a senior moment?





Steven McKinney

Statistician
Molecular Oncology and Breast Cancer Program
British Columbia Cancer Research Centre

email: smckinney at bccrc.ca

tel: 604-675-8000 x7561

BCCRC
Molecular Oncology
675 West 10th Ave, Floor 4
Vancouver B.C. 
V5Z 1L3
Canada

> with(df, interaction(A, B))
[1] a.b a.x x.x x.x
Levels: x.x a.x x.b a.b
> A.B <- factor(with(df, interaction(A, B)))
> A.B
[1] a.b a.x x.x x.x
Levels: x.x a.x a.b
> model.matrix(~ A.B, df)
  (Intercept) A.B[T.a.x] A.B[T.a.b]
1           1          0          1
2           1          1          0
3           1          0          0
4           1          0          0
attr(,"assign")
[1] 0 1 1
attr(,"contrasts")
attr(,"contrasts")$A.B
[1] "contr.Treatment"
>