KPSS.2.breaks.unknown: KPSS-test with 2 unknown structural breaks

View source: R/KPSS.2.breaks.R

KPSS.2.breaks.unknownR Documentation

KPSS-test with 2 unknown structural breaks

Description

Procedure to compute the KPSS test with two structural breaks

Usage

KPSS.2.breaks.unknown(y, model, max.lag = 0, kernel = "bartlett")

Arguments

y

A time series of interest.

model

A scalar equal to

  • 1: for the AA (without trend) model,

  • 2: for the AA (with trend) model,

  • 3: for the BB model,

  • 4: for the CC model,

  • 5: for the AC-CA model.

max.lag

A scalar, with the maximum order of the parametric correction. The final order of the parametric correction is selected using the BIC information criterion.

kernel

Kernel for calculating long-run variance

  • bartlett: for Bartlett kernel,

  • quadratic: for Quadratic Spectral kernel,

  • NULL for the Kurozumi's proposal, using Bartlett kernel.

Details

The break points are known

The code provided is the original GAUSS code ported to R.

See Carrion-i-Silvestre and Sansó (2007) for further details.

Value

Value of test statistic.

References

Carrion-i-Silvestre, Josep Lluís, and Andreu Sansó. “Testing the Null of Cointegration with Structural Breaks.” Oxford Bulletin of Economics and Statistics 68, no. 5 (October 2006): 623–46. https://doi.org/10.1111/j.1468-0084.2006.00180.x.


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