urca (version 0.2-0)

ur.kpss: Kwiatkowski et al. Unit Root Test

Description

Performs the KPSS Unit Root Test, where the Null hypothesis is stationarity. The test types specify as deterministic component either a constant (mu) or a constant with linear trend (tau).

Usage

ur.kpss(y, type = c("mu", "tau"), lags = c("short", "long", "nil"),
        use.lag = NULL)

Arguments

y

Vector to be tested for a unit root.

type

Type of deterministic part.

lags

Maximum number of lags used for error term correction.

use.lag

User specified number of lags.

Value

• An object of class "ur.kpss".

Details

lags="short" sets the number of lags to 4*(n/100)^0.25, whereas lags="long" sets the number of lags to 12*(n/100)^0.25. If lags="nil" is choosen, then no error correction is made. Furthermore, one can specify a different number of maximum lags by seting use.lag accordingly.

References

Kwiatkowski, D., Phillips, P.C.B., Schmidt, P. and Shin, Y., (1992), Testing the Null Hypothesis of Stationarity Against the Alternative of a Unit Root: How Sure Are We That Economic Time Series Have a Unit Root?, Journal of Econometrics, 54, 159--178. Download possible at: http://cowles.econ.yale.edu/, see rubric 'Discussion Papers (CFDPs)'.

See Also

ur.kpss-class

Examples

data(nporg)
gnp <- na.omit(nporg[, "gnp.r"])
gnp.l <- log(gnp)
kpss.gnp <- ur.kpss(gnp.l, type="tau", lags="short")
summary(kpss.gnp)