GeomComb (version 1.0)

comb_InvW: Inverse Rank Forecast Combination

Description

Computes forecast combination weights according to the inverse rank approach by Aiolfi and Timmermann (2006) and produces forecasts for the test set, if provided.

Usage

comb_InvW(x)

Arguments

x

An object of class foreccomb. Contains training set (actual values + matrix of model forecasts) and optionally a test set.

Value

Returns an object of class foreccomb_res with the following components: with the following components:

Details

In the inverse rank approach by Aiolfi and Timmermann (2006), the combination weights are inversely proportional to the forecast model's rank, $Rank_i$:

$$w_i^{InvW} = \frac{Rank_i^{-1}}{\Sigma_{j=1}^N Rank_j^{-1}}$$

The combined forecast is then obtained by:

$$\hat{y}_t = {\mathbf{f}_{t}}'\mathbf{w}^{InvW}$$

This is a robust variant of the Bates/Granger (1969) approach and also ignores correlations across forecast errors.

References

Aiolfi, M., amd Timmermann, A. (2006). Persistence in Forecasting Performance and Conditional Combination Strategies. Journal of Econometrics, 135(1), 31--53.

Bates, J. M., and Granger, C. W. (1969). The Combination of Forecasts. Journal of the Operational Research Society, 20(4), 451--468.

See Also

foreccomb, plot.foreccomb_res, summary.foreccomb_res, comb_BG, accuracy

Examples

obs <- rnorm(100)
preds <- matrix(rnorm(1000, 1), 100, 10)
train_o<-obs[1:80]
train_p<-preds[1:80,]
test_o<-obs[81:100]
test_p<-preds[81:100,]

data<-foreccomb(train_o, train_p, test_o, test_p)
comb_InvW(data)