vcov.tcensReg: Method for Returning Covariance of Fixed Parameters for...

In tcensReg: MLE of a Truncated Normal Distribution with Censored Data

Description

Method for Returning Covariance of Fixed Parameters for tcensReg S3 Objects

Usage

## S3 method for class 'tcensReg'
vcov(object, logsigma = FALSE, ...)

Arguments

object	Object of class tcensReg
logsigma	Logical indicator of whether to return standard deviation as logsigma or sigma. Default is FALSE returning sigma
...	Additional optional parameters

Details

If logsigma=TRUE, the default variance covariance matrix is returned. Otherwise if the parameter sigma is desired then logsigma=FALSE, and we use the multivariate delta method to find these values as described below:

Original Asymptotic Result:

θ=(β_{1}, …, β_{(p-1)}, \log(σ))^{T}\sim N_{p}(\hat{θ}, \hat{Σ}_{θ})

Transformed Parameters:

g(θ)=(β_{1}, …, β_{(p-1)}, \exp\{\log(σ)\})^{T}\sim N_{p}(g(\hat{θ}), \nabla_{g(θ)}^{T}\hat{Σ}_{θ}\nabla_{g(θ)})

The gradient vector is defined as

\nabla_{g(θ)}=diag(1_{p-1}, \log(σ)\exp\{\log(σ)\})_{p\times p}

Value

Numeric matrix of variance covarince values

tcensReg documentation built on July 8, 2020, 7:17 p.m.