coint.test.GH: Gregory-Hansen test for the absense of cointegration

In d9d6ka/RANEPA-R: Set of unit root and cointegration tests

Gregory-Hansen test for the absense of cointegration

Description

Gregory and Hansen (1996) test for the null hypothesis of no cointegration under a possible structural break at the unknown moment of time.

The authors proposed ADF- and Z-type tests, slightly modified to allow the presence of a possible regime shift. Three type of shifts are allowed:

• a shift in the constant,

• a shift in the constand with the trend included,

• and a shift in the constant and the cointegrating vector.

Critical values are calculated via the adopted MacKinnon procedure of estimating the model for the response surface.

Usage

coint.test.GH(
  ...,
  shift = "level",
  trim = 0.15,
  max.lag = 10,
  criterion = "aic",
  add.criticals = TRUE
)

Arguments

...	Variables of interest.
shift	Expected break type.
trim	The trimming parameter to calculate break moment bounds.
max.lag	The maximum number of lags for the internal ADF testing.
criterion	The criterion for lag selection.
add.criticals	Whether critical values are to be returned. This argument is needed to suppress the calculation of critical values during the precalculation of tables needed for the p-values estimating.

Value

An object of type cointGH. It's a list of

• shift: shift type,

• Za: MZ_\alpha statistic and c.v.,

• Zt: MZ_t statistic and c.v.,

• ADF: ADF statistic and c.v..

References

MacKinnon, James G. “Critical Values for Cointegration Tests.” Working Paper. Working Paper. Economics Department, Queen’s University, January 2010. https://ideas.repec.org/p/qed/wpaper/1227.html.

Gregory, Allan W., and Bruce E. Hansen. “Residual-Based Tests for Cointegration in Models with Regime Shifts.” Journal of Econometrics 70, no. 1 (January 1, 1996): 99–126. https://doi.org/10.1016/0304-4076(69)41685-7.

d9d6ka/RANEPA-R documentation built on May 4, 2024, 7:11 a.m.