select.forecast.cov
Select forecast covariances meeting given criteria
Description
Select forecast covariances meeting given criteria.
Usage
select.forecast.cov(obj, select.series=1,
select.cov.best=1,
select.cov.bound=NULL,
verbose=T)
Required Arguments
- obj
-
An object as returned by mine.strip.
Optional Arguments
- select.series
-
An indication of series to which the tests should be applied.
- select.cov.best
-
The number of 'best' forecasts to select.
- select.cov.bound
-
A bound to use as criteria for selection.
- verbose
-
If verbose=T then summary results are printed.
Value
The returned result is a forecast.cov object like obj, but filtered
to remove models which do not meet criteria.
Details
Select models with forecast covariance for select.series meeting criteria.
The default select.cov.best=1 selects the best model at each horizon.
select.cov.best=3 would select the best 3 models at each horizon.
If select.cov.bound is not NULL then select.cov.best is ignored and
any model which is better than the bound at all horizons is selected.
select.cov.bound can be a vector of the same length as select.series,
in which case corresponding elements are applied to the different series.
See Also
Examples
z <- select.forecast.cov(obj)
plot(select.forecast.cov(obj, select.cov.bound=20000))
plot(select.forecast.cov(obj, select.cov.best=3))
return to Table of Contents