bootstrapfun: Function to perform parametric bootstrap

In GaussianHMM1d: Inference, Goodness-of-Fit and Forecast for Univariate Gaussian Hidden Markov Models

Function to perform parametric bootstrap

Description

This function simulates the data under the null hypothesis of a Gaussian HMM and compute the Cramér-von Mises test statistic.

Usage

bootstrapfun(mu, sigma, Q, max_iter, prec, n)

Arguments

mu	vector of means for each regime (r x 1);
sigma	vector of standard deviations for each regime (r x 1);
Q	transition probality matrix (r x r);
max_iter	maximum number of iterations of the EM algorithm; suggestion 10 000;
prec	precision (stopping criteria); suggestion 0.0001;
n	length of the time series.

Value

f	values of the density function at time n+k
w	weights of the mixture

Author(s)

Bouchra R Nasri and Bruno N Rémillard, January 31, 2019

References

Chapter 10.2 of B. Rémillard (2013). Statistical Methods for Financial Engineering, Chapman and Hall/CRC Financial Mathematics Series, Taylor & Francis.

Examples

mu <- c(-0.3 ,0.7) ; sigma <- c(0.15,0.05); Q <- matrix(c(0.8, 0.3, 0.2, 0.7),2,2) ;
data <- Sim.HMM.Gaussian.1d(mu,sigma,Q,eta0=1,100)$x
out <- bootstrapfun(mu,sigma,Q,max_iter=10000,prec=0.0001,n=100)

GaussianHMM1d documentation built on July 9, 2023, 6:52 p.m.