Abstracts - faqs.org

Abstracts

Economics

Search abstracts:
Abstracts » Economics

Flexible regression models and relative forecast performance

Article Abstract:

Alternative flexible nonlinear models like Neural Networks, Projection Pursuit models and Random fields regression model approach are examined and their performance is evaluated depending on various measures of out-of-sample forecast accuracy. The results show that the comparison between real-time forecast accuracy based on the flexible regression model and real-time forecast accuracy of linear specification can help in using flexible regression models as a tool for identifying nonlinear components.

Author: Dahl, Christian M., Hylleberg, Svend
Publisher: Elsevier B.V.
Publication Name: International Journal of Forecasting
Subject: Economics
ISSN: 0169-2070
Year: 2004
Regression analysis, Real-time data processing, Real time data processing

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


Extreme value theory and value-at-risk: relative performance in emerging markets

Article Abstract:

The relative performance of Value-at-Risk (VaR) models is examined in relation to the daily stock market returns of the different emerging markets. The Generalized Pareto Distribution and the extreme value theory (EVT) method play a very important role in risk management and in determining the VaR calculations of the emerging markets, thus providing an understanding of the dynamic structure of the emerging markets.

Author: Gencay, Ramazan, Selcuk, Faruk
Publisher: Elsevier B.V.
Publication Name: International Journal of Forecasting
Subject: Economics
ISSN: 0169-2070
Year: 2004
Marketing procedures, Science & research, Research Findings, Financial Services, Finance and Insurance, DEPOSITORY INSTITUTIONS, Asset & Risk Management, Research, Financial services industry, Risk management, Marketing research, Emerging markets, Market research

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


The performance of SETAR models: a regime conditional evaluation of point, interval and density forecasts

Article Abstract:

The out-of-sample performance of self-exciting threshold autoregressive (SETAR) models in relation to a linear autoregression (AR) and a generalized autoregressive conditional heteroskedastic (GARCH) model is evaluated on the basis of point, interval and density forecasts. GARCH models outperform the SETAR models but the performance of the SETAR models improves under conditionally specific regimes.

Author: Boero, Gianna, Marrocu, Emanuela
Publisher: Elsevier B.V.
Publication Name: International Journal of Forecasting
Subject: Economics
ISSN: 0169-2070
Year: 2004
Analysis, Foreign exchange rates, Density functionals, Density functional theory, Autoregression (Statistics)

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


Subjects list: Models
Similar abstracts:
  • Abstracts: VAR, error correction and pretest forecasts at long horizons. Specifying and testing output and pricing structures of alternative macroeconomic models
  • Abstracts: Employee involvement programmes improve corporate performance. Corporate raiders don't cut investment in R&D
  • Abstracts: Transaction costs and partnerships: the case of the rock bands. Transaction costs, technology transfer, and in-house R&D: a study of the Indian private corporate sector
  • Abstracts: Risk reduction be diversification in the Nordic stock markets. Computationally convenient optimal intertemporal portfolios under linear constraints
  • Abstracts: Inflation, corruption, and income distribution: the recent price reform in China. Permanent income and long-run stability in a generalized multiplier/accelerator model
This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.
Some parts © 2025 Advameg, Inc.