This function computes the variance-covariance matrix of variance components (VC) either applying the approach given in the 1st reference ('method="scm"') or using the approximation given in the 2nd reference ('method="gb"').
1 |
obj |
(VCA) object |
method |
(character) string, optionally specifying whether to use the algorithm given in the 1st reference ("scm") or in the 2nd refernce ("gb"). If not not supplied, the option is used coming with the 'VCA' object. |
quiet |
(logical) TRUE = will suppress any warning, which will be issued otherwise |
When 'method="scm"' is used function getVCvar
is called implementing this rather
time-consuming algorithm. Both approaches, respectively the results they generate, diverge for
increasing degree of unbalancedness. For balanced designs, they seem to differ only due to
numerical reasons (error propagation).
This function is called on a 'VCA' object, which can be the sole argument. In this case the value
assigned to element 'VarVC.method' of the 'VCA' object will be used
(see getVCvar
for computational details).
(matrix) corresponding to variance-covariance matrix of variance components
Andre Schuetzenmeister andre.schuetzenmeister@roche.com
Searle, S.R, Casella, G., McCulloch, C.E. (1992), Variance Components, Wiley New York
Giesbrecht, F.G. and Burns, J.C. (1985), Two-Stage Analysis Based on a Mixed Model: Large-Sample Asymptotic Theory and Small-Sample Simulation Results, Biometrics 41, p. 477-486
1 2 3 4 5 6 7 8 9 |
Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
Please suggest features or report bugs with the GitHub issue tracker.
All documentation is copyright its authors; we didn't write any of that.