Modelling exchange rate dynamics: new perspectives from the frequency domain

Article Abstract:

Forecasting the distribution of foreign exchange rates is more successful when a nonlinear, multiplicative method is applied which uses techniques of spectral analysis. A study of a series of ten foreign exchange rates indicates that non-Gaussianity and nonlinearity were present, and this was supported by McLeod-Li and Tsay tests. Two models based on nonlinearity and polyspectral analysis proved to be the only models of a group of seven which predicted outcomes better than a random-walk approach. A full analysis of the tests is included.

Foreign exchange market

---

Guaranteed-content prediction intervals for non-linear autoregressions

Article Abstract:

The construction of more predictable content time intervals enables better forecasting. Prediction intervals are shifted toward expected biases. This method doesn't deal with contrary time series.

Sweden, Economics, Statistical Data Included, Methods, Time, Autoregression (Statistics)

---

Are forecasters reluctant to revise their predictions? Some German evidence

Article Abstract:

The failure of economists in revising their forecasting models is discussed by focusing on forecasting hypothesis followed by Association of German Economic Research Institute.

Government expenditures, Germany, Economists, Economic policy, Beliefs, opinions and attitudes

Similar abstracts:

• Abstracts: Testing and valuing dynamic correlations for asset allocation. On the fit of new Keynesian models
• Abstracts: Forecasting an aggregate of cointegrated disaggregates. Forecasting for the Generation of Trading Signals in Financial Markets
• Abstracts: Equilibrium analysis of an economy with innovations. Dynamic Cournot oligopolies with production adjustment costs
• Abstracts: Monitoring for outliers and level shifts in Kalman filter implementations of exponential smoothing. Exponential smoothing of seasonal data: a comparison
• Abstracts: A forecasting comparison of classical and Bayesian methods for modelling logistic diffusion. A cautionary note on outlier robust estimation of threshold modelsn

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