bcVAR {bcVAR} | R Documentation |
Estimation of the Bias-corrected LS of a VAR(p) model.
bcVAR(data = data, p = 1, constant = TRUE, ...)
data |
Data item containing the endogenous variables. |
p |
Integer for the lag order (default is p = 1). |
constant |
If constant = TRUE, a intercept vector is included in the model. |
... |
Not used. |
Estimates a VAR by OLS and applies the bias correction of Pope, A. L. (1990). The model is of the following form:
\bold{y}_t = [\bold{v}, A_1, …, A_p] + \bold{u}_t,
where \bold{y}_t is a K \times 1 vector of endogenous variables and \bold{u}_t is assumed to be iid white noise. The coefficient matrices A_1, …, A_p are of dimension K \times K. The intercept vector \bold{v} is of dimension K \times 1. The LS estimator is
\hat{A} = [\hat{\bold{v}}, \hat{A}_1, …, \hat{A}_p] = YZ'(ZZ')^-1,
where...
A list with class attribute ‘varest
’ holding the
following elements:
varresult |
list of ‘ |
datamat |
The data matrix of the endogenous and explanatory variables. |
y |
The data matrix of the endogenous variables. |
p |
An integer specifying the lag order. |
K |
An integer specifying the dimension of the VAR. |
obs |
An integer specifying the number of used observations. |
totobs |
An integer specifying the total number of observations. |
restrictions |
Always |
call |
The |
Simon Röck
Pope, A. L. (1990), Biases of estimators in multivariate non-gausssian autoregressions, Journal of Time Series Analysis.
Kilian, L., & Lütkepohl, H. (2017), Structural Vector Autoregressive Analysis, Cambridge University Press, Cambridge.
## load data of package data("USmacro", package = "bcVAR") ## detrend data (substract mean) dataDT <- apply(USmacro, 2, function(y) y - mean(y)) ## example for a bias-corrected LS VAR(4) model (see Chapter 2 of Kilian, L., & Lütkepohl, H. (2017)) bcVAR(dataDT, p = 4, constant = TRUE)