marx.t: The estimation of the MARX model by t-MLE function

In MARX: Simulation, Estimation, Model Selection and Forecasting for MARX Models

Description

This function allows you to estimate the MARX model by t-MLE.

Usage

marx.t(y, x, p_C, p_NC, params0)

Arguments

y	Data vector of time series observations.
x	Matrix of data (every column represents one time series). Specify NULL or "not" if not wanted.
p_C	Number of lags.
p_NC	Number of leads.
params0	Starting values for the parameters to be estimated (both model and distributional parameters).

Value

coef.c	Estimated causal coefficients.
coef.nc	Estimated noncausal coefficients.
coef.exo	Estimated exogenous coefficients.
coef.int	Estimated intercept.
scale	Estimated scale parameter.
df	Estimated degrees of freedom.
residuals	Residuals.
se.dist	Standard errors of the distributional parameters.

Author(s)

Sean Telg

Examples

data <- sim.marx(c('t',3,1),c('t',3,1),100,0.5,0.4,0.3)
marx.t(data$y,data$x,1,1)

Example output

$coef.c
[1] 0.3435036

$coef.nc
[1] 0.4482843

$coef.exo
[1] 0.3602371

$coef.int
[1] -0.0007735896

$scale
[1] 1.002721

$df
[1] 2.878963

$residuals
 [1] -0.112437039  0.591265265  0.787010861 -0.122115267 -1.484140064
 [6]  0.001678685 -1.177051996  3.430558904  1.489499284 -2.277838004
[11] -0.245163630 -1.020948707 -0.572439083  2.378330290 -1.111749202
[16]  1.213763728 -0.032353231  0.036053838  7.028472784  3.369210490
[21] -0.387951283  1.110670829  2.023123065 -2.836225299  0.919648320
[26]  0.975323874  0.124070050  1.073047373 -0.998145608 -0.494442149
[31] -0.220317791 -4.051714690 -1.551627533  0.501805224  0.046339345
[36] -1.469577937  0.200402708 -1.164507008  1.094488283  0.444882090
[41]  0.375066069  2.022488679 -1.292328803 -0.371091933  2.722126444
[46]  1.076539366 -1.456742454  0.132968141 -1.706730719  0.132425918
[51]  2.688787556 -0.649598530 -3.141155734  2.421487991 -0.793765334
[56] -0.005109873 -0.553428996  0.213755205  1.313355643  0.372318699
[61] -0.041520926 -0.479082736  0.536395230 -1.375999519 -2.547114961
[66]  0.239048575 -0.087715252  0.486639065 -1.719749442 -0.387375710
[71]  0.025924188  0.514015911 -0.060349165 -0.276547459  1.470836494
[76]  2.383577219 -3.186565313 -0.622378967 -1.468313928 -0.363586327
[81]  1.266412388 -0.595887475  0.699901960 -0.061600904 -0.078025846
[86] -0.152573949  0.110884484 -1.129736705  0.676222895 -0.257331448
[91]  0.614805373  0.168246469  3.664362574 -0.118483495 -0.210995942
[96]  1.807843084  0.301286129 -1.904757880

$se.dist
[1] 1.172622 0.162562

Warning messages:
1: In sqrt(df1 * pi * sig1^2) : NaNs produced
2: In log(1 + (E/sig1)^2/df1) : NaNs produced

MARX documentation built on May 2, 2019, 3:42 a.m.