> I am using the Design library and robcov to compute
> variance-covariance matrices for clustered data
> Is there an easy way to compute the F-test (i.e.
> linear hypothesis) for clustered data regression ?
> Thanks in advance!
Once you adjust for clustering using robcov or bootcov, only Wald
chi-square tests are available.
Frank E Harrell Jr Professor and Chair School of Medicine
Department of Biostatistics Vanderbilt University