Comparing the accuracy of density forecasts from competing models

Article Abstract:

The importance of evaluating the forecast accuracy of empirical models on the basis of density (as opposed to point) forecasting performance is emphasized by a growing body of literature. To prove the null hypothesis that two competing models have equal density forecast accuracy, a test statistic is introduced. The test is easy to use and Monte Carlo simulations suggest the test has satisfactory size and power properties. The use of the test is illustrated through an application to exchange rate forecasting.

Forecasts, trends, outlooks, Forecasts and trends, Foreign exchange, Foreign exchange rates, Market trend/market analysis

---

A reply to Armstrong and Fildes

Article Abstract:

The Generalized Forecast Error Second Moment (GFESM) is an improvement over the Mean Square Forecasting Error (MSFE) because GFESM measures are invariant to non-singular, scale-preserving linear transformations, unlike MSFE measures. Empirically irrelevant assumptions may be used as a positive guide. In fact, the Monte Carlo simulation illustrates the importance of the invariance of GSFEM.

Research

---

Robust evaluation of fixed-event forecast rationality

Article Abstract:

A likelihood estimator is used to evaluate fixed-event forecasts in terms of rationality. The underlying data contributes to ambivalent test results.

Economics, Research and Development in the Social Sciences and Humanities, Statistical Data Included

Similar abstracts:

• Abstracts: Choosing the number of conditioning events in judgemental forecasting. Going up-going down: how good are people at forecasting trends and changes in trends?
• Abstracts: Evaluating the rationality of fixed-event forecasts. Cross-correlations and predictability of stock returns. Evaluating the predictive accuracy of volatility models
• Abstracts: Modelling exchange rate dynamics: new perspectives from the frequency domain. Guaranteed-content prediction intervals for non-linear autoregressions

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.