Consistent Monitoring of Stationarity and Cointegrating Relationships

We propose a consistent monitoring procedure to detect a structural change from a cointegrating relationship to a spurious relationship. The procedure is based on residuals from modified least squares estimation, using either Fully Modified, Dynamic or Integrated Modified OLS. It is inspired by Chu et al. (1996) in that it is based on parameter estimation on a pre-break "calibration" period only, rather than being based on sequential estimation over the full sample. See the discussion paper for further information. This package provides the monitoring procedures for both the cointegration and the stationarity case (while the latter is just a special case of the former one) as well as printing and plotting methods for a clear presentation of the results.


Consistent Monitoring of Stationarity and Cointegrating Relationships.

  • Installation (including latest CRAN version of cointReg)
install.packages("cointReg")
devtools::install_github("aschersleben/cointmonitoR", build_vignettes = TRUE)
library("cointmonitoR")
  • Simple example (stationarity, structural break):
set.seed(1909)
eps <- rnorm(200)
x <- c(eps[1:100], cumsum(eps[101:200]) / 2)
test <- monitorStationarity(x, m = 93)
print(test)
oldpar <- par(mfrow = c(2, 1))
plot(test, what = "both", legend = FALSE)
par(oldpar)
  • Package vignette: Provides further examples and explanations.
vignette("cointmonitoR")
  • Package help page: Overview of all available functions:
package?cointmonitoR
devtools::install_github("aschersleben/cointmonitoR", build_vignettes = TRUE)

We propose a consistent monitoring procedure to detect a structural change from a cointegrating relationship to a spurious relationship. The procedure is based on residuals from modified least squares estimation, using either Fully Modified, Dynamic or Integrated Modified OLS. It is inspired by Chu et al. (1996) in that it is based on parameter estimation on a pre-break "calibration" period only, rather than being based on sequential estimation over the full sample.

See the discussion paper for further information.

This package provides the monitoring procedures for both the cointegration and the stationarity case (the latter is just a special case of the former one) as well as printing and plotting methods for a clear presentation of the results.

  • Aschersleben, P. and M. Wagner (2016). cointReg: Parameter Estimation and Inference in a Cointegrating Regression. R package version 0.2.0. https://CRAN.R-project.org/package=cointReg

  • Chu, C.J., M. Stinchcombe and H. White (1996): "Monitoring Structural Change", Econometrica, 64, 1045--1065, DOI:10.2307/2297912.

  • Wagner, M. and D. Wied (2015): "Monitoring Stationarity and Cointegration," Discussion Paper, DOI:10.2139/ssrn.2624657

News

cointmonitoR 0.1 (2016-06-14)

  • First CRAN release version of the package.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("cointmonitoR")

0.1.0 by Philipp Aschersleben, 9 months ago


https://github.com/aschersleben/cointmonitoR


Report a bug at https://github.com/aschersleben/cointmonitoR/issues


Browse source code at https://github.com/cran/cointmonitoR


Authors: Philipp Aschersleben [aut, cre], Martin Wagner [aut] (Author of underlying paper.), Dominik Wied [aut] (Author of underlying paper.)


Documentation:   PDF Manual  


GPL-3 license


Imports stats, graphics, matrixStats

Depends on cointReg

Suggests knitr, rmarkdown


See at CRAN