Hi,
I notice that the Matrix::sparse.model.matrix produces inconsistent matrix
when the contrasts is a sparse matrix.
Here is a minimal example:
```r
library(Matrix)
class(CO2[[1]]) <- class(CO2[[2]]) <- "factor"
get_contr <- function(is_sparse) {
contr <- list()
contr[["Plant"]] <- contrasts(CO2[[1]], FALSE, sparse = is_sparse)
contr[["Type"]] <- contrasts(CO2[[2]], FALSE, sparse = is_sparse)
contr[["Treatment"]] <- contrasts(CO2[[3]], FALSE, sparse = is_sparse)
contr
}
m1 <- sparse.model.matrix(~.^2, CO2, get_contr(TRUE))
m2 <- sparse.model.matrix(~.^2, CO2, get_contr(FALSE))
dim(m1)
dim(m2)
```
The dimension is different:
> dim(m1)
[1] 84 66
> dim(m2)
[1] 84 104
>
The example should be reproduced with docker image rocker/r-base
Wush
PhD Student of Graduate Institute of Electrical Engineering, National
Taiwan University
[[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.
