stationary.test: Stationary Test for Univariate Time Series

In aTSA: Alternative Time Series Analysis

Stationary Test for Univariate Time Series

Description

Performs stationary test for a univariate time series.

Usage

stationary.test(x, method = c("adf", "pp", "kpss"), nlag = NULL,
  type = c("Z_rho", "Z_tau"), lag.short = TRUE, output = TRUE)

Arguments

x	a numeric vector or univariate time series.
method	a character indicating which test to use. The default is "adf" by Augmented Dickey-Fuller test.
nlag	the lag order to calculate the test statistic, only valid for method = "adf". See adf.test for more details.
type	the test type, only valid for method = "pp". See pp.test for more details.
lag.short	a logical value, only valid for method = "pp" or "kpss". See pp.test and kpss.test for more details.
output	a logical value indicating to print the results in R console. The default is TRUE.

Details

This function combines the existing functions adf.test, pp.test and kpss.test for testing the stationarity of a univariate time series x.

Value

The results are the same as one of the adf.test, pp.test, kpss.test, depending on which test are used.

Note

Missing values are removed.

Author(s)

Debin Qiu

Examples

x <- arima.sim(list(order = c(1,0,0),ar = 0.2),n = 100)
stationary.test(x)  # same as adf.test(x)
stationary.test(x, method = "pp") # same as pp.test(x)
stationary.test(x, method = "kpss") # same as kpss.test(x)

aTSA documentation built on May 29, 2024, 8:50 a.m.