vcov2 {lavaSearch2}

Variance-Covariance With Small Sample Correction

Description

Extract the variance-covariance matrix from a latent variable model. Similar to stats::vcov but with small sample correction.

Usage

vcov2(object, robust, cluster, as.lava, ...)

## S3 method for class 'lvmfit'
vcov2(
  object,
  robust = FALSE,
  cluster = NULL,
  as.lava = TRUE,
  ssc = lava.options()$ssc,
  ...
)

## S3 method for class 'lvmfit2'
vcov2(object, robust = FALSE, cluster = NULL, as.lava = TRUE, ...)

## S3 method for class 'lvmfit2'
vcov(object, robust = FALSE, cluster = NULL, as.lava = TRUE, ...)

Arguments

object

a lvmfit or lvmfit2 object (i.e. output of lava::estimate or lavaSearch2::estimate2).

robust

[logical] should robust standard errors be used instead of the model based standard errors? Should be TRUE if argument cluster is not NULL.

cluster

[integer vector] the grouping variable relative to which the observations are iid.

as.lava

[logical] if TRUE, uses the same names as when using stats::coef.

...

additional argument passed to estimate2 when using a lvmfit object.

ssc

[character] method used to correct the small sample bias of the variance coefficients: no correction ("none"/FALSE/NA), correct the first order bias in the residual variance ("residual"), or correct the first order bias in the estimated coefficients "cox"). Only relevant when using a lvmfit object.

Details

When argument object is a lvmfit object, the method first calls estimate2 and then extract the variance-covariance matrix.

Value

A matrix with as many rows and columns as the number of coefficients.

See Also

estimate2 to obtain lvmfit2 objects.

Examples

#### simulate data ####
n <- 5e1
p <- 3
X.name <- paste0("X",1:p)
link.lvm <- paste0("Y~",X.name)
formula.lvm <- as.formula(paste0("Y~",paste0(X.name,collapse="+")))

m <- lvm(formula.lvm)
distribution(m,~Id) <- Sequence.lvm(0)
set.seed(10)
d <- lava::sim(m,n)

#### linear models ####
e.lm <- lm(formula.lvm,data=d)

#### latent variable models ####
e.lvm <- estimate(lvm(formula.lvm),data=d)
vcov0 <- vcov(e.lvm)
vcovSSC <- vcov2(e.lvm)

vcovSSC/vcov0
vcovSSC[1:4,1:4]/vcov(e.lm)