The impact of seasonal constants on forecasting seasonally cointegrated time series

Article Abstract:

Analysis of the effects of deleting, restricting or not restricting seasonal intercept terms on forecasting sets reveals that predictive performance of models are often improved by restricting. However, there are relative advantages and disadvantages of using the three techniques across data sets and that it may depend on features that are sample-specific, thus denoting different effects depending on the way data is treated.

Author: Franses, Philip Hans, Kunst, Robert M.
Seasonal variations (Economics)

User Contributions:

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

CAPTCHA


Forecasting with money demand functions: the UK case

Article Abstract:

Analysis of time instability variable effects on error-correction money demand function forecasting techniques reveals that the cointegration approach and multivariate error correction models do not fare better than the standard. The standard ARIMA specs and ad-hoc simple reduced-form models are generally better performers than out-of-sample forecasting.

Author: Garcia-Ferrer, Antonio, Novales, Alfonso
Money demand

User Contributions:

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

CAPTCHA


Forecasting high-frequency financial data with the ARFIMA-ARCH model

Article Abstract:

An Autoregressive Fractionally Integrated Moving Average-Autoregressive Conditional Heteroskedasticity model was used for high frequency financial information forecasting. This model is effective for volatility forecasts.

Author: Hauser, Michael A., Kunst, Robert M.
Austria, Models, Autoregression (Statistics), Time-series analysis, Time series analysis

User Contributions:

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

CAPTCHA


Subjects list: Methods, Analysis, Economics, Econometrics, Economic forecasting, Business models
This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.