nep-for New Economics Papers
on Forecasting
Issue of 2006‒09‒11
four papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting Realized Volatility by Decomposition By Markku Lanne
  2. Forecasting Emerging Market Indicators: Brazil and Russia By Victor Bystrov
  3. Institutional Forecasting: The Performance of Thin Virtual Stock Markets By Bruggen, G.H. van; Spann, M.; Lilien, G.L.; Skiera, B.
  4. Real-time forecasting and political stock market anomalies: evidence for the U.S. By Bohl, Martin; Döpke, Jörg; Pierdzioch, Christian

  1. By: Markku Lanne
    Abstract: Forecasts of the realized volatility of the exchange rate returns of the Euro against the U.S. Dollar obtained directly and through decomposition are compared. Decomposing the realized volatility into its continuous sample path and jump components and modeling and forecasting them separately instead of directly forecasting the realized volatility is shown to lead to improved out-of-sample forecasts. Moreover, gains in forecast accuracy are robust with respect to the details of the decomposition.
    Keywords: Mixture model, Jump, Realized volatility, Gamma distribution
    JEL: C22 C52 C53 G15
    Date: 2006
  2. By: Victor Bystrov
    Abstract: The adoption of inflation targeting in emerging market economies makesaccurate forecasting of inflation and output growth in these economies of primary importance. Since only short spans of data are available for such markets, autoregressive and small-scale vector autoregressive models can be suggested as forecasting tools. However,these models include only a few economic time series from the whole variety of data available to forecasters. Therefore dynamic factor models, extracting information from a large number of time series, can be suggested as a reasonable alternative. In this paper two approaches are evaluated on the basis of data available for Brazil and Russia. The results allow us to suggest that the forecasting performance of the models considered depends on the statistical properties of the series to be forecast, which are affected by structural changes and changes in operating regime. This interaction between the statistical properties of the series and the forecasting performance of models requires more detailed investigation.
    Keywords: forecasting, emerging markets, factor models
    JEL: C53 C32 E37
    Date: 2006
  3. By: Bruggen, G.H. van; Spann, M.; Lilien, G.L.; Skiera, B. (Erasmus Research Institute of Management (ERIM), RSM Erasmus University)
    Abstract: We study the performance of Virtual Stock Markets (VSMs) in an institutional forecasting environment. We compare VSMs to the Combined Judgmental Forecast (CJF) and the Key Informant (KI) approach. We find that VSMs can be effectively applied in an environment with a small number of knowledgeable informants, i.e., in thin markets. Our results show that none of the three approaches differ in forecasting accuracy in a low knowledge-heterogeneity environment. However, where there is high knowledge-heterogeneity, the VSM approach outperforms the CJF approach, which in turn outperforms the KI approach. Hence, our results provide useful insight into when each of the three approaches might be most effectively applied.
    Keywords: Virtual Stock Markets;Forecasting;Information Markets;Electronic Markets;
    Date: 2006–06–23
  4. By: Bohl, Martin; Döpke, Jörg; Pierdzioch, Christian
    Abstract: Using monthly data for the period 1953–2003, we apply a real-time modeling approach to investigate the implications of U.S. political stock market anomalies for forecasting excess stock returns. Our empirical findings show that political variables, selected on the basis of widely used model selection criteria, are often included in real-time forecasting models. However, they do not contribute to systematically improving the performance of simple trading rules. For this reason, political stock market anomalies are not necessarily an indication of market inefficiency.
    Keywords: Political stock market anomalies, predictability of stock returns, efficient markets hypothesis, real-time forecasting
    JEL: G11 G14
    Date: 2006

This nep-for issue is ©2006 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.