Hello
I am running a simulation study to assess the type I error rate of a likelihood
ratio test. This requires me to minimize over restricted spaces under the null
and under the alternative hypothesis. My problem is that occassionally I run
into an error message that reads: "Error in solve.default(cov, ...) :
Lapack routine dgesv: system is exactly singular" when I make a call to
"nlminb". The negative log likelihood function being minimized is
based on the multivariate normal distribution. Can anyone help me with the
source of such an error message? Or better still how to get at the source?
Thanks,
SP: opomporay at yahoo.com
____________________________________________________________________________________
Got a little couch potato?
Check out fun summer activities for kids.
