Parameter estimation and tests of equal forecast accuracy between non - nested models

Article Abstract:

The effects of estimated model parameters on tests of equal forecast accuracy between non -nested models are reviewed. A new method is proposed to reduce the instances of wrong assumptions and the method is proved with Monte Carlo evidence.

---

Effects of temporal aggregation on estimates and forecasts of fractionally integreated processes: a Mote - Carlo study

Article Abstract:

The effects of temporal aggregation on the estimated long memory parameter using parametric and semi - parametric methods are analyzed. The aggregated forecasts are compared with the non-aggregated series for forecast comparison.

---

A comparison of financial duration models via density forecasts

Article Abstract:

A comparison of predictive performance of econometric specifications developed for modeling duration process in intra-day financial markets is done using density forecast evaluation methods.

Netherlands, Germany, Forecasts, trends, outlooks, Belgium, Forecasts and trends, Market trend/market analysis, Financial markets, Econometric models

Similar abstracts:

• Abstracts: Heterogeneous expectations and tests of efficiency in the yen/dollar forward exchange rate market. Expectations, the Exchange Rate, and the Current Account
• Abstracts: Differential information and optimal feedback policy in new classical macroeconomic models. Forecasting with a nonlinear dynamic model of stock returns and industrial production
• Abstracts: A reexamination of analysts' earnings forecasts for takeover targets. The impact of industry shocks on takeover and restructuring activity
• Abstracts: Time series concepts for conditional distributions. Selecting a nonlinear time series model using weighted tests of equal forecast accuracy
• Abstracts: Comparative statics of fixed points. An equivalence principle for perfectly competitive economics

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