adjCov: Adjustment for the covariance matrix from a fitted...

Description Usage Arguments Details Value WARNINGS Author(s) References See Also

View source: R/adjCov.r

Description

adjCov can be used to adjust the covariance matrix of a fitted SemiParBIV, copulaReg, copulaSampleSel, SemiParTRIV object.

Usage

1
adjCov(x, id)

Arguments

x

A fitted SemiParBIV, copulaReg, copulaSampleSel, SemiParTRIV object as produced by the respective fitting function.

id

Cluster identifier.

Details

This adjustment can be made when dealing with clustered data and the cluster structure is neglected when fitting the model. The basic idea is that the model is fitted as though observations were independent, and subsequently adjust the covariance matrix of the parameter estimates. Using the terminology of Liang and Zeger (1986), this would correspond to using an independence structure within the context of generalized estimating equations. The parameter estimators are still consistent but are inefficient as compared to a model which accounts for the correct cluster dependence structure. The covariance matrix of the independence estimators can be adjusted as described in Liang and Zeger (1986, Section 2).

Value

This function returns a fitted object which is identical to that supplied in adjCov but with adjusted covariance matrix.

WARNINGS

This correction may not be appropriate for models fitted using penalties.

Author(s)

Maintainer: Giampiero Marra [email protected]

References

Liang K.-Y. and Zeger S. (1986), Longitudinal Data Analysis Using Generalized Linear Models. Biometrika, 73(1), 13-22.

See Also

JRM-package, SemiParBIV, summary.SemiParBIV, SemiParTRIV, summary.SemiParTRIV, copulaReg, summary.copulaReg, copulaSampleSel, summary.copulaSampleSel


JRM documentation built on July 13, 2017, 5:03 p.m.