pseudo: The pseudo-causal model function

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

Description

This function allows you to estimate pseudo-causal ARX models by OLS (compatible with most functions in lm() class).

Usage

pseudo(y, x, p)

## Default S3 method:
pseudo(y, x, p)

## S3 method for class 'pseudo'
print(x, ...)

## S3 method for class 'pseudo'
summary(object, ...)

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	Number of lags to be included.
...	Other arguments
object	An object of the class "pseudo"

Value

An object of class "pseudo" is a list containing the following components:

coefficients	Vector of estimated coefficients.
coef.auto	Vector of estimated autoregressive parameters.
coef.exo	Vector of estimated exogenous parameters.
mse	Mean squared error.
residuals	Residuals.
loglikelihood	Value of the loglikelihood.
fitted.values	Fitted values.
df	Degrees of freedom.
vcov	Variance-covariance matrix of residuals.

Examples

data <- sim.marx(c('t',1,1), c('t',1,1),100,0.5,0.4,0.3)
object <- pseudo(data$y, data$x, 2)
class(object) <- "pseudo"
summary(object)

Example output

$call
pseudo.default(y = data$y, x = data$x, p = 2)

$coefficients
        Estimate    Std.Err    t value      p value
int    3.9742567 3.02612323  1.3133162 1.922732e-01
lag 1  0.9908056 0.09746286 10.1659816 8.162422e-17
lag 2 -0.3220194 0.09591093 -3.3574841 1.136743e-03
exo 1  0.2761263 0.31153786  0.8863332 3.777000e-01

attr(,"class")
[1] "summary.pseudo"

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