forecastCovReductionsWRTtrue: Forecast covariance for different models

Description Usage Arguments Details Value

View source: R/dse2.R

Description

Calculate the forecast covariance for different models.

Usage

1
2
3
4
5
6
   forecastCovReductionsWRTtrue(true.model, rng=NULL,
                       simulation.args=NULL,
                       est.replications=2, pred.replications=2,
                       discard.before=10, horizons=1:12,quiet=FALSE,
                       estimation.methods=NULL,
                       criteria=NULL, compiled=.DSEflags()$COMPILED) 

Arguments

true.model

An object of class TSmodel or TSestModel.

discard.before

An integer indicating the number of points in the beginning of forecasts to discard for calculating covariances.

est.replications

an interger indicating the number of times simulation and estimation are repeated.

pred.replications

an argument passed to forecastCovWRTtrue.

simulation.args

A list of any arguments which should be passed to simulate in order to simulate the true model.

horizons

Horizons for which forecast covariance should be calculated.

rng

If specified then it is used to set RNG.

quiet

If TRUE then some messages are not printed.

estimation.methods

a list as used by estimateModels.

criteria

a ...

compiled

a logical indicating if compiled code should be used. (Usually true except for debugging.)

Details

Calculate the forecasts cov of reduced models estimated from simulations of true.model with an estimation method indicated by estimation.methods. (estimation.methods is as in estimation.models BUT ONLY THE FIRST IS USED.) discard.before is an integer indicating 1+the number of points in the beginning of forecasts to discard for calculating forecast covariances. criteria can be a vector of criteria as in informationTests, (eg c("taic", "tbic") in which case the "best" model for each criteria is accounted separately. (ie. it is added to the beginning of the list of estimated models)

Value

A list ...


dse documentation built on March 26, 2020, 7:12 p.m.