vcov: Extract Covariance Matrix Parameter Estimates from Objects of...

In metaSEM: Meta-Analysis using Structural Equation Modeling

Extract Covariance Matrix Parameter Estimates from Objects of Various Classes

Description

It extracts the variance-covariance matrix of the parameter estimates from objects of various classes.

Usage

## S3 method for class 'tssem1FEM'
vcov(object, ...)
## S3 method for class 'tssem1FEM.cluster'
vcov(object, ...)
## S3 method for class 'tssem1REM'
vcov(object, select = c("all", "fixed", "random"), robust=FALSE, ...)
## S3 method for class 'wls'
vcov(object, ...)
## S3 method for class 'wls.cluster'
vcov(object, ...)
## S3 method for class 'meta'
vcov(object, select = c("all", "fixed", "random"), robust=FALSE, ...)
## S3 method for class 'meta3LFIML'
vcov(object, select = c("all", "fixed", "random","allX"), robust=FALSE, ...)
## S3 method for class 'reml'
vcov(object, ...)
## S3 method for class 'MxRAMModel'
vcov(object, ...)
## S3 method for class 'osmasem'
vcov(object, select=c("fixed", "all", "random"), robust=FALSE, ...)

Arguments

object	An object returned from objects of various classes
select	Select all for both fixed- and random-effects parameters, fixed for the fixed-effects parameters or random for the random-effects parameters. For meta3LFIML objects, allX is used to extract all parameters including the predictors and auxiliary variables.
robust	Logicial. Whether to use robust standard error from imxRobustSE.
...	Further arguments; currently not in use except for tssemRobust1, which to be passed to robust.

Value

A variance-covariance matrix of the parameter estimates.

Note

vcov returns NA when the diag.constraints=TRUE argument is used in wls objects.

Author(s)

Mike W.-L. Cheung <[e-mail]>

See Also

tssem1, wls, meta, reml

Examples

## Random-effects meta-analysis
model1 <- meta(y=yi, v=vi, data=Hox02)
vcov(model1)

## Fixed-effects only
vcov(model1, select="fixed")

## Random-effects only
vcov(model1, select="random")

metaSEM documentation built on Aug. 10, 2023, 1:09 a.m.