Title: A Joint Test-Statistic for the Null of Non-Cointegration
Version: 0.2.0
Description: Implements a joint cointegration testing approach that combines Engle-Granger, Johansen maximum eigenvalue, Boswijk, and Banerjee tests into a unified test-statistic for the null of non-cointegration. Also see Bayer and Hanck (2013) <doi:10.1111/j.1467-9892.2012.00814.x>.
License: MIT + file LICENSE
BugReports: https://github.com/Janine-Langerbein/combcoint/issues
Depends: R (≥ 3.6.0)
Imports: dplyr, Hmisc, magrittr, purrr, stats, stringr, tibble, tidyr, tsDyn, urca
Suggests: MTS, knitr, rmarkdown, testthat (≥ 3.0.0)
VignetteBuilder: knitr
Config/testthat/edition: 3
Encoding: UTF-8
LazyData: true
RoxygenNote: 7.3.2
URL: https://github.com/Janine-Langerbein/combcoint
NeedsCompilation: no
Packaged: 2025-06-11 13:34:14 UTC; LS_Statistik
Author: Janine Langerbein [aut, cre, cph], Jens Klenke ORCID iD [aut]
Maintainer: Janine Langerbein <janine.langerbein@icloud.com>
Repository: CRAN
Date/Publication: 2025-06-13 19:40:05 UTC

Pipe operator

Description

See magrittr::%>% for details.

Usage

lhs %>% rhs

Arguments

lhs

A value or the magrittr placeholder.

rhs

A function call using the magrittr semantics.

Value

The result of calling 'rhs(lhs)'.

Cointegration Tests

Description

Executes common cointegration tests, which serve as underlying tests for the Bayer Hanck Test statistic.

Usage

banerjee(formula, data, lags = 1, trend = "const")

boswijk(formula, data, lags = 1, trend = "const")

englegranger(formula, data, lags = 1, trend = "const")

johansen(formula, data, type = "eigen", lags = 1, trend = "const")

Arguments

formula

An object of class formula to describe the model.

data

An optional data frame containing the variables in the model.

lags

Number of lags to be included.

trend

Type of deterministic component to be inlcuded, "none" for no deterministics, "const" for a constant and "trend" for a constant plus trend.

type

Test to be conducted, either "eigen" or "trace".

Value

Returns an object of class "list".

Functions

References

Engle, R. and Granger, C. (1987), Co-integration and Error Correction: Representation, Estimation, and Testing, Econometrica 55(2), 251-76.

Johansen, S. (1988), Statistical analysis of cointegration vectors, Journal of Economic Dynamics and Control 12(2-3), 231-254.

Banerjee, A., Dolado, J. J. and Mestre, R. (1998), Error-correction Mechanism Tests for Cointegration in a Single-equation Framework, Journal of Times Series Analysis 19(3), 267-283.

Boswijk, H. P. (1994), Testing for an unstable root in conditional and structural error correction models, Journal of Econometrics 63(1), 37-60.

Examples

# Luetkepohl (2007): Economic data from West Germany
data(lutkepohl_e1)
englegranger(linvestment ~ lincome + lconsumption, data = lutkepohl_e1)

#' @examplesIf requireNamespace("MTS", quietly = TRUE)
# World Almanac and Book of Facts (1975): Monthly simple returns of the stocks of IBM,
# Coca Cola and S&P Composite index
try({
  data("mts-examples", package = "MTS")
  englegranger(sp ~ ibm + ko, data = ibmspko)
}, silent = TRUE)

Joint Test-Statistic for the Null of Non-Cointegration

Description

Produces a joint test-statistic for the null of non-cointegration, aggregating various cointegration tests.

Usage

bayerhanck(formula, data, lags = 1, trend = "const", test = "all")

Arguments

formula

An object of class formula to describe the model.

data

An optional data frame containing the variables in the model.

lags

Number of lags to be included.

trend

Type of deterministic component to be included. "none" for no deterministic, "const" for a constant and "trend" for a constant plus trend.

test

Selection of tests to choose from. Choices are either "ej", for englegranger and johansen, or "all", for englegranger, johansen, banerjee and boswijk.

Value

bayerhanck returns an object of classes "bhtest" and "list".

The function summary is used to print a summary, which includes the test statistics and p-values for the underlying tests, as well as the test statistic and p-value for the Bayer Hanck Test.

An object of class "bhtest" is a "list" containing, inter alia, the components:

bh.test

the test statistic of the Bayer Hanck Test.

bh.pval

the p-Value of the Bayer Hanck Test.

test.stat

the test statistics of the underlying tests.

pval.stat

the p-values of the underlying tests.

References

Bayer, C. and Hanck, C. (2013). Combining non-cointegration tests. Journal of Time Series Analysis, 34(1), 83 – 95. doi:10.1111/j.1467-9892.2012.00814.x

Examples

# Luetkepohl (2007): Economic data from West Germany
data(lutkepohl_e1)
bayerhanck(linvestment ~ lincome + lconsumption, data = lutkepohl_e1)
bayerhanck(linvestment ~ lincome + lconsumption, data = lutkepohl_e1, lags = 4)



# World Almanac and Book of Facts (1975): Monthly simple returns of the stocks of IBM,
# Coca Cola and S&P Composite index
try({
  data("mts-examples", package = "MTS")
  bayerhanck(sp ~ ibm + ko, data = ibmspko)
}, silent = TRUE)

Economic data from West Germany

Description

The data was retrieved from the E1 file of Luetkepohl (2007) and contains quarterly, seasonally adjusted data for fixed investment, disposable income, and consumption expenditures in billions of DM (Deutsche Mark, West German currency before the Euro) from the first quarter of 1960 until the fourth quarter of 1982 for West Germany. The raw data is available at http://www.jmulti.de/download/datasets/e1.dat.

Usage

data(lutkepohl_e1)

Format

A data frame with 92 rows and 10 variables:

investment

fixed investment.

income

disposable income.

consumption

consumption expenditures.

qtr

time vector in quarterly intervals.

linvestment

log of fixed investment.

dlinvestment

first difference of the log of fixed investment.

lincome

log of disposable income.

dlincome

first difference of the log of disposable income.

lconsumption

log of consumption expenditures.

dlconsumption

first difference of the log of consumption expenditures.

References

Luetkepohl, (2006). New introduction to multiple time series analysis (2nd ed.). Berlin: Springer.