Calculates density values of the null distribution in the Durbin Watson test. Uses the saddlepoint approximation by Paolella (2007).
Usage
ddw(x, mod, data = list())
Value
Numerical density value(s).
Arguments
x
quantile value(s) at which the density should be determined.
mod
estimated linear model object, formula (with argument data specified), or model matrix.
data
if mod is a formula then the name of the corresponding dataframe has to be specified here.
Details
The Durbin Watson Null-Distribution depends on values of the exogenous variables. That is why it must be calculated from each specific data set, respectively.
References
Durbin, J. & Watson, G.S. (1950): Testing for Serial Correlation in Least Squares Regression I. Biometrika 37, 409-428.
Paolella (2007): Intermediate Probability - A Computational Approach, Wiley.