Evaluation of correlation forecasting models for risk management

Article Abstract:

Correlation forecasting techniques are compared using standard statistical and risk management loss functions. GARCH models better explain correlations in stock and bond portfolios, while simpler moving average models suit the currency portfolio better.

Greece, Commercial Banks, Investment Banking and Securities Dealing, Portfolio Management, Asset & Risk Management, Portfolio & Funds Management, Models, Risk management, Report

---

A Bayesian nonlinear support vector machine error correction model

Article Abstract:

A study on effectiveness of using nonlinear support vector correction models within Bayesian framework, based on stationarity and cointegration analysis estimated with least squares regression, for financial time series prediction, is presented.

Belgium, Time-series analysis, Time series analysis

---

Validating multiple-period density-forecasting models

Article Abstract:

The validation of multiple-period density-forecasting models used for long-term forecasting of business performance, based on the density forecasts of economic variables is presented.

Evaluation, Econometric models

Similar abstracts:

• Abstracts: A comparison of approximate Bayesian forecasting methods for non-Gaussian time series. ARMA models and the Box-Jenkins methodology
• Abstracts: Validation of volatility models. A Bayesian analysis of periodic integration
• Abstracts: Econometric modelling for short-term inflation forecasting in the euro area. Forecasting Euro area inflation using dynamic factor measures of underlying inflation
• Abstracts: Testing the rationality of forecast revisions made by the IMF and the OECD. Political maneuverings as sources of measurement errors in forecasts
• Abstracts: Assessing the historical accuracy of regional economic forecasts. Regional econometric income forecast accuracy

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