rmixlm: Random data generation from the mixture of Gaussian linear...

In hhsmm: Hidden Hybrid Markov/Semi-Markov Model Fitting

Random data generation from the mixture of Gaussian linear (Markov-switching) models for hhsmm model

Description

Generates vectors of covariate and response observations from mixture of Gaussian linear (Markov-switching) models in a specified state and using the parameters of a specified model

Usage

rmixlm(j, model, covar, ...)

Arguments

j	a specified state
model	a hhsmmspec model
covar	either a function which generates the covariate vector or a list containing the following items: mean the mean vector of covariates (to be generated from multivariate normal distribution) cov the variance-covariance matrix of covariates (to be generated from multivariate normal distribution)
...	additional arguments of the covar function

Value

a random matrix of observations from mixture of Gaussian linear (Markov-switching) models, in which the first columns are associated with the responses and the last columns are associated with the covariates

Author(s)

Morteza Amini, [e-mail]

References

Kim, C. J., Piger, J. and Startz, R. (2008). Estimation of Markov regime-switching regression models with endogenous switching. Journal of Econometrics, 143(2), 263-273.

Examples

J <- 3
initial <- c(1, 0, 0)
semi <- rep(FALSE, 3)
P <- matrix(c(0.5, 0.2, 0.3, 0.2, 0.5, 0.3, 0.1, 0.4, 0.5), nrow = J, 
byrow = TRUE)
par <- list(intercept = list(3, list(-10, -1), 14),
coefficient = list(-1, list(1, 5), -7),
csigma = list(1.2, list(2.3, 3.4), 1.1),
mix.p = list(1, c(0.4, 0.6), 1))
model <- hhsmmspec(init = initial, transition = P, parms.emis = par,
dens.emis = dmixlm, semi = semi)

#use the covar as the list of mean and 
#variance of the normal distribution 

train1 <- simulate(model, nsim = c(20, 30, 42, 50), seed = 1234, 
remission = rmixlm, covar = list(mean = 0, cov = 1))
plot(train1$x[,1] ~ train1$x[,2], col = train1$s, pch = 16, 
xlab = "x", ylab = "y")

#use the covar as the runif function 
#to generate one covariate from standard uniform distribution 

train2 <- simulate(model, nsim = c(20, 30, 42, 50), seed = 1234, 
remission = rmixlm, covar = runif, 1)
plot(train2$x[,1] ~ train2$x[,2], col = train2$s, pch = 16, 
xlab = "x", ylab = "y")

hhsmm documentation built on Aug. 8, 2023, 9:06 a.m.