[R-sig-ME] large dataset - lmer2 vector size specified is too large

Gregor Gorjanc gregor.gorjanc at bfro.uni-lj.si
Fri Mar 2 16:07:20 CET 2007


Douglas Bates <bates at ...> writes:
...
> but even that formula means that you are estimating 448 fixed effects
> for which the model matrix is of size 448 * 43680 * 8 bytes (about 150
> MB).  In addition you are attempting to estimate

Not directly related. Is it really necessary to build model matrix i.e. X. 
Building X'X directly would be more efficient i.e. only 448 * 448 * 8 bytes.

Gregor




More information about the R-sig-mixed-models mailing list