ast-infomat: Information Matrix Function of Asymmetric Student-t...

In dan9401/st: Asymmetric Student t-distributions

Description

Information matrix, asymptotic covariance and correlation matrix functions of Asymmetric Student-t distribution

Usage

astInfoMat(pars, data = c(), method = c("expected", "observed"))

astCov(pars)

astCor(pars)

Arguments

pars	a vector of parameter values for an AST distribution
data	a vector of numeric data used to calculate observed information matrix
method	one of "expected" and "observed", calculating the expected / observed information matrix

Details

The expected information matrix is calculated by the expectation of the outer product of score functions, analytical formulas are provided in Zhu and Galbraith(2010). The observed information matrix is calculated by the expectation of negative Hessian Matrix of the log-likelihood function.

References

Zhu, D., & Galbraith, J. W. (2010). A generalized asymmetric Student-t distribution with application to financial econometrics. Journal of Econometrics, 157(2), 297-305.https://www.sciencedirect.com/science/article/pii/S0304407610000266 https://econpapers.repec.org/paper/circirwor/2009s-13.htm

Examples

pars <- c(0.12, 0.6, 0.6, 3, 5)
data <- rast(1000, pars = pars)
round(astInfoMat(pars, data, "observed"), 4)
round(astInfoMat(pars, "expected"), 4)
round(astCov(pars), 4)
round(astCor(pars), 4)

dan9401/st documentation built on Sept. 5, 2020, 5:16 a.m.