uroot (version 1.3)

ADF.test: Augmented Dickey-Fuller test

Description

This function computes the augmented Dickey-Fuller statistic for testing the null hypothesis that exists a unit root at the zero frequency.

Usage

ADF.test (label, compdet, selecP, Mvfic, VFEp, showcat)

Arguments

label

a list object with information about the series. The list consists of the following elements. vari, a ts object with the data of the series, s, the periodicity of the series (4, 12, or 1 for quarterly, monthly, or anual data),

compdet

a vector indicating the deterministic components included in the auxiliar regression.

selecP

method for selecting lags included in the auxiliar regression.

Mvfic

a matrix containing any particular dummy.

VFEp

a matrix containing partial seasonal dummies.

showcat

how the results are showed and stored. If TRUE a brief explanation reports the results. If FALSE a list object stores the results.

Value

• ADF test statistic for long run unit root hypothesis, coefficient and t-statistics of the deterministic components, and number of available observations.

Details

compdet is a numeric vector of length three. If an element is equal to 1 it indicates that a constant, linear trend, or seasonal dummies, respectively are included. Otherwise, the element must be set to zero.

Mvfic and VFEp are two kinds of dummies. The first one is a generic dummy and any 0-1 column-matrix can be designed for it. The second one includes seasonal dummies for only some, not necessarily all of the seasons.

Available lag selection methods are the following: aiclb is based on the AIC criterion and Ljung-Box test, biclb is based on the BIC criterion and Ljung-Box test, aiclut follows a top-down strategy based on the AIC criterion, biclut follows a top-down strategy based on the BIC criterion, signf retains the significant lags. It is also possible to set the argument selecP equals to a vector, for instance, SelecP=c(1,3,4) for those lags to be included in the auxiliar regression.

References

D.A. Dickey and W.A. Fuller (1981), Likelihood ratio statistics for autoregressive time series with a unit root. Econometrica, 49, 1057-1071.

W.A. Fuller (1976), Introduction to Statistical Time Series. Jonh Wiley, New York.

Examples

## ADF.test with constant and seasonal dummies and without other dummies.
     data(AirPassengers)
     AirP <- list(vari=AirPassengers, s=12, t0=c(1949,1), N=length(AirPassengers))
     ADF.test(label=AirP, compdet=c(1,0,1), selecP="biclb", Mvfic=0, VFEp=0, showcat=TRUE)