vcov function

Variance-Covariance Matrix of smam Estimators

This function calculates variance covariance matrix for estimators from smam package. Different methods will be used for different smam models.

## S3 method for class 'smam_mrme'
vcov(
  object,
  nBS = 25,
  detailBS = TRUE,
  numThreads = 5,
  gradMethod = "simple",
  vcovMethod = "pBootstrap",
  integrControl = integr.control(),
  ...
)

## S3 method for class 'smam_mm'
vcov(
  object,
  nBS = 25,
  detailBS = TRUE,
  numThreads = 5,
  integrControl = integr.control(),
  ...
)

## S3 method for class 'smam_mrh'
vcov(object, numThreads = 5, integrControl = integr.control(), ...)

## S3 method for class 'smam_mr'
vcov(object, ...)

## S3 method for class 'smam_bmme'
vcov(object, ...)

Arguments

• object: a fitted object from one of smam::fitXXXX functions

• nBS: number of bootstrap.

• detailBS: whether or not output estimation results of bootstrap, which can be used to generate bootstrap CI. Required when vcovMethod=='pBootstrap'.

• numThreads: the number of threads for parallel computation. If its value is greater than 1, then parallel computation will be processed. Otherwise, serial computation will be processed.

• gradMethod: method used for numeric gradient (numDeriv::grad). Required when vcovMethod=='Godambe'.

• vcovMethod: method of calculating variance covariance matrix. This should be one of pBootstrap (default) and Godambe.

• integrControl: a list of control parameters for the integrate

  function: rel.tol, abs.tol, subdivision.

• ...: Optional arguments that are not used

Examples

## time consuming example
#tgrid <- seq(0, 100, length=100)
#set.seed(123)
#dat <- rMRME(tgrid, 1, 0.5, 1, 0.01, "m")

## fit whole dataset to the MRME model
#fit <- fitMRME(dat, start=c(1, 0.5, 1, 0.01))
#fit

## get covariance matrix of estimators
#vcov(fit)