MSARmdl {MSTest}R Documentation

Markov-switching autoregressive model

Description

This function estimates a Markov-switching autoregressive model

Usage

MSARmdl(Y, p, k, control = list())

Arguments

Y

(T x 1) vector with observational data.

p

integer for the number of lags to use in estimation. Must be greater than or equal to 1.

k

integer for the number of regimes to use in estimation. Must be greater than or equal to 2.

control

List with model options including:

  • getSE: Boolean. If TRUE standard errors are computed and returned. If FALSE standard errors are not computed. Default is TRUE.

  • msmu: Boolean. If TRUE model is estimated with switch in mean. If FALSE model is estimated with constant mean. Default is TRUE.

  • msvar: Boolean. If TRUE model is estimated with switch in variance. If FALSE model is estimated with constant variance. Default is TRUE.

  • init_theta: vector of initial values. vector must contain (1 x q) vector mu, vech(sigma), and vec(P) where sigma is a (q x q) covariance matrix.This is optional. Default is NULL, in which case initVals_MSARmdl is used to generate initial values.

  • method: string determining which method to use. Options are 'EM' for EM algorithm or 'MLE' for Maximum Likelihood Estimation.

  • maxit: integer determining the maximum number of EM iterations.

  • thtol: double determining the convergence criterion for the absolute difference in parameter estimates theta between iterations. Default is 1e-6.

  • maxit_converge: integer determining the maximum number of initial values attempted until solution is finite. For example, if parameters in theta or logLike are NaN another set of initial values (up to maxit_converge) is attempted until finite values are returned. This does not occur frequently for most types of data but may be useful in some cases. Once finite values are obtained, this counts as one iteration towards use_diff_init. Default is 500.

  • use_diff_init: integer determining how many different initial values to try (that do not return NaN; see maxit_converge). Default is 1.

  • mle_stationary_constraint: Boolean determining if only stationary solutions are considered (if TRUE) or not (if FALSE). Default is TRUE.

  • mle_variance_constraint: Double used to determine the lower bound for variance in each regime. Value should be between 0 and 1 as it is multiplied by single regime variance. Default is 0.01 (i.e., 1% of single regime variance.

  • mle_theta_low: Vector with lower bounds on parameters (Used only if method = "MLE"). Default is NULL.

  • mle_theta_upp: Vector with upper bounds on parameters (Used only if method = "MLE"). Default is NULL.

Value

List of class MSARmdl (S3 object) with model attributes including:

References

Dempster, A. P., N. M. Laird, and D. B. Rubin. 1977. “Maximum Likelihood from Incomplete Data via the EM Algorithm.” Journal of the Royal Statistical Society. Series B 39 (1): 1–38..

Hamilton, James D. 1990. “Analysis of time series subject to changes in regime.” Journal of econometrics, 45 (1-2): 39–70.

See Also

ARmdl

Examples

# --------------------------- Use simulated process ----------------------------
set.seed(1234)
# Define DGP of MS AR process
mdl_ms2 <- list(n     = 200, 
                mu    = c(5,10),
                sigma = c(1,4),
                phi   = c(0.5),
                k     = 2,
                P     = rbind(c(0.90, 0.10),
                              c(0.10, 0.90)))

# Simulate process using simuMSAR() function
y_ms_simu <- simuMSAR(mdl_ms2)

# Set options for model estimation
control <- list(msmu   = TRUE, 
                msvar  = TRUE, 
                method = "EM",
                use_diff_init = 1)

# Estimate model

  ms_mdl <- MSARmdl(y_ms_simu$y, p = 1, k = 2, control)
  summary(ms_mdl)





[Package MSTest version 0.1.2 Index]