t_test: Test the significance of the parameters of an ARIMA model

In nmecsys/BETS: Brazilian Economic Time Series

Description

Performs the t test on every parameter of an ARIMA model. This model can be an Arima or an arima.

Usage

t_test(model, nx = 0, alpha = 0.05)

Arguments

model	An Arima or an arima object. The model for which the parameters must be tested.
nx	An integer. The number of exogenous variables
alpha	A numeric value between 0 and 1. The significance level.

Value

A data.frame containing the standard erros, the t-statistic, the critical values and whether the null hypothesis should be rejected or not, for each model parameter.

Author(s)

Talitha Speranza [e-mail], Daiane Marcolino [e-mail]

Examples

require(forecast)
data("AirPassengers")
fit.air<- Arima(AirPassengers,order = c(1,1,1), seasonal = c(1,1,1), method ="ML",lambda=0)
summary(fit.air)

# Significance test for the model SARIMA(1,1,1)(1,1,1)[12]
t_test(model = fit.air)

nmecsys/BETS documentation built on April 8, 2021, 1:54 a.m.