When including the interest rate into my time series model against the exchange rate, I attempt to carry out a Lagrange multiplier test to show whether there exists autocorrelation between the interest rate lags. When I run this for one lag:
var interestrate, lag(1/1)
varlmar
it outputs a table. However when I run the command for 4 lags:
var interestrate, lag(1/4)
varlmar
the output is as follows: "
the lags of residuals may not be collinear with the dependent variables, or their lags
the output is as follows: "
"
Could anyone shed some light on this issue and any potential ways to rectify this problem.
Thanks,
Luke
Could anyone shed some light on this issue and any potential ways to rectify this problem.
Thanks,
Luke
0 Response to Testing for serial correlation between the interest rate and its lags
Post a Comment