cointReg {cointReg}R Documentation

Estimation and Inference for cointegrating regressions


Computes either the Phillips and Hansen (1990) Fully Modified OLS estimator, or the Saikkonen (1990) Dynamic OLS estimator, or the Vogelsang and Wagner (2014) Integrated Modified OLS estimator.


cointReg(method = c("FM", "D", "IM"), x, y, ...)



Select the method for the estimation of your cointegration model:


[numeric | matrix | data.frame]
RHS variables on which to apply the model estimation.


[numeric | matrix | data.frame]
LHS variable(s) on which to apply the model estimation. Usually one-dimensional, but a matrix or data.frame with more than one column is also possible (only for FM-OLS).


Arguments passed to the corresponding cointReg function, like:

  • x, y, deter: data to include in the model

  • kernel, bandwidth: parameters for calculating the long-run variance

  • n.lead, n.lag, kmax, info.crit: D-OLS specific arguments.

  • selector, t.test: IM-OLS specific arguments.

  • check: Wheather to check (and if necessary convert) the arguments. See checkVars for further information.


[cointReg] object.


See Also

Other cointReg: cointRegD, cointRegFM, cointRegIM, plot.cointReg, print.cointReg


x1 = cumsum(rnorm(100, mean = 0.05, sd = 0.1))
x2 = cumsum(rnorm(100, sd = 0.1)) + 1
x3 = cumsum(rnorm(100, sd = 0.2)) + 2
x = cbind(x1, x2, x3)
y = x1 + x2 + x3 + rnorm(100, sd = 0.2) + 1
deter = cbind(level = 1, trend = 1:100)
cointReg("FM", x = x, y = y, deter = deter, kernel = "ba",
         bandwidth = "and")

# Compare the results of all three models:
res = sapply(c("FM", "D", "IM"), cointReg, x = x, y = y, deter = deter), lapply(res, "[[", "theta"))

[Package cointReg version 0.2.0 Index]