nep-for New Economics Papers
on Forecasting
Issue of 2006‒07‒15
thirteen papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting Inflation: the Relevance of Higher Moments By Jane M. Binner
  2. Forecasting Financial Crises and Contagion in Asia using Dynamic Factor Analysis By Andrea Cipollini
  3. Forecasting Irregularly Spaced UHF Financial Data: Realized Volatility vs UHF-GARCH Models By Francois-Éric Racicot; Raymond Théoret; Alain Coen
  4. Forecasting the Term Structure of Variance Swaps By Kai Detlefsen; Wolfgang Härdle
  5. Currency Predictions for Multi-Currency Instruments By Baldur P. Magnusson; Daniel R. Plante
  6. Forecasting stock prices using Genetic Programming and Chance Discovery By Alma Lilia Garcia-Almanza; Edward P.K. Tsang
  7. Exchange Rates and Fundamentals: Is there a Role for Nonlinearities in Real Time? By Yunus Aksoy; ; Kurmas Akdogan
  8. Learning to Forecast the Exchange Rate: Two Competing Approaches. By Paul De Grauwe
  9. The predictive power of the present value model of stock prices By Geraldine Ryan
  10. The discounted economic stock of money with VAR forecasting By William A. Barnett; U. of Kansas
  11. Forcasting in large cointegrated processes By Hiroaki Chigira; Taku Yamamoto
  12. Growth and Longevity from the Industrial Revolution to the Future of an Aging Society By de la Croix, David; Lindh, Thomas; Malmberg, Bo
  13. Understanding rural change - demography as a key to the future By Amcoff, Jan; Westholm, Erik

  1. By: Jane M. Binner (Aston University)
    Keywords: relative price distribution, higher moments, out-of-sample inflation forecasting
    JEL: C22 C43 E27
    Date: 2006–07–04
  2. By: Andrea Cipollini (University of Essex)
    Keywords: Financial Contagion, Dynamic Factor Model, Stochastic Simulation
    JEL: C32 C51 F34
    Date: 2006–07–04
  3. By: Francois-Éric Racicot (Département des sciences administratives, Université du Québec (Outaouais) et LRSP); Raymond Théoret (Département de stratégie des affaires, Université du Québec (Montréal)); Alain Coen (Département de stratégie des affaires, Université du Québec (Montréal))
    Abstract: A very promising literature has been recently devoted to the modeling of ultra-high-frequency (UHF) data. Our first aim is to develop an empirical application of Autoregressive Conditional Duration GARCH models and the realized volatility to forecast future volatilities on irregularly spaced data. We also compare the out sample performances of ACD GARCH models with the realized volatility method. We propose a procedure to take into account the time deformation and show how to use these models for computing daily VaR.
    Keywords: Realized volatility, Ultra High Frequency GARCH, time deformation, financial markets, Daily VaR.
    JEL: C22 C53 G14
    Date: 2006–07–06
  4. By: Kai Detlefsen; Wolfgang Härdle
    Abstract: Recently, Diebold and Li (2003) obtained good forecasting results for yield curves in a reparametrized Nelson-Siegel framework. We analyze similar modeling approaches for price curves of variance swaps that serve nowadays as hedging instruments for options on realized variance. We consider the popular Heston model, reparametrize its variance swap price formula and model the entire variance swap curves by two exponential factors whose loadings evolve dynamically on a weekly basis. Generalizing this approach we consider a reparametrization of the three-dimensional Nelson-Siegel factor model. We show that these factors can be interpreted as level, slope and curvature and how they can be estimated directly from characteristic points of the curves. Moreover, we analyze a semiparametric factor model. Estimating autoregressive models for the factor loadings we get termstructure forecasts that we compare in addition to the random walk and the static Heston model that is often used in industry. In contrast to the results of Diebold and Li (2003) on yield curves, no model produces better forecasts of variance swap curves than the random walk but forecasting the Heston model improves the popular static Heston model. Moreover, the Heston model is better than the flexible semiparametric approach that outperforms the Nelson-Siegel model.
    Keywords: Term structure, Variance swap curve, Heston model, Nelson-Siegel curve, Semiparametric factor model
    JEL: G1 D4 C5
    Date: 2006–07
  5. By: Baldur P. Magnusson; Daniel R. Plante
    Keywords: Currency Forecasting, Neural Networks, Brownian Motion
    Date: 2006–07–04
  6. By: Alma Lilia Garcia-Almanza (COMPUTER SCIENCE UNIVERSITY OF ESSEX); Edward P.K. Tsang
    Keywords: Forecasting, Chance discovery, Genetic programming, machine learning
    Date: 2006–07–04
  7. By: Yunus Aksoy; ; Kurmas Akdogan
    Keywords: monetary model, exchange rates, nonlinear adjustment, real time, unit roots, forecasting
    JEL: F31 F37
    Date: 2006–07–04
  8. By: Paul De Grauwe (KULeuven)
    Keywords: Exchange Rate Economics, Adaptive Learning, Behavioral Finance
    JEL: F31 F41
    Date: 2006–07–04
  9. By: Geraldine Ryan (Economics University College Cork)
    Keywords: Present Value Model of Stock Prices; Nonlinear Unit Root Tests; Nonlinear Cointegration Tests; ESTAR- EGARCH model; Long Horizon Predictability Tests.
    JEL: G12 G14 C53
    Date: 2006–07–04
  10. By: William A. Barnett; U. of Kansas
    Keywords: Monetary aggregation, discounted economic capital stock, VAR, robustness, capital asset pricing
    JEL: E41 G12 C43 C22
    Date: 2006–07–04
  11. By: Hiroaki Chigira; Taku Yamamoto
    Abstract: It is widely recognized that taking cointegration relationships into consideration is useful in forecasting cointegrated processes. However, there are a few practical problems when forecasting large cointegrated processes using the well-known vector error correction model. First, it is hard to identify the cointegration rank in large models. Second, since the number of parameters to be estimated tends to be large relative to the sample size in large models, estimators will have large standard errors, and so will forecasts. The purpose of the present paper is to propose a new procedure for forecasting large cointegrated processes, which is free from the above problems. In our Monte Carlo experiment, we find that our forecast gains accuracy when we work with a larger model as long as the ratio of the cointegration rank to the number of variables in the process is high.
    Keywords: Forcasting, Cointegration, Large Models
    JEL: C12 C32
    Date: 2006–06
  12. By: de la Croix, David (Université catholique de Louvain); Lindh, Thomas (Institute for Futures Studies); Malmberg, Bo (Institute for Futures Studies)
    Abstract: Aging of the population will affect the growth path of all countries. To assess the historical and future importance of this claim we use two popular approaches and evaluate their merits and disadvantages by confronting them to Swedish data. We first simulate an endogenous growth model with human capital linking demographic changes and income growth. Rising longevity increases the incentive to get education, which in turn has ever-lasting effects on growth through a human capital externality. Secondly, we consider a reduced-form statistical model based on the demographic dividend literature. Assuming that there is a common DGP guiding growth through the demographic transition, we use an estimate from post-war global data to backcast the Swedish historical GDP growth. Comparing the two approaches, encompassing tests show that each of them contains independent information on the Swedish growth path, suggesting that there is a benefit from combining them for long-term forecasting.
    Keywords: aging population; growth path; long-term forecasting
    JEL: J11
    Date: 2006–06
  13. By: Amcoff, Jan (Institute for Futures Studies); Westholm, Erik (Institute for Futures Studies)
    Abstract: The last decades have seen a rapidly growing interest in foresight methodology. Methods have been developed in corporate and governmental communication exercises often labelled technology foresight. In reality, these foresights have often drifted into processes of social change, since technological change is hard to foresee beyond what is already in the pipe-line. Forecasting of social change, however, must be based on solid knowledge about the mechanisms of continuity and change. Virtually nothing can be said about the future without relating to the past; foresights and futures studies are about revealing the hidden pulse of history. Hence, the answer to forecasting the future is empirical research within the social sciences. <p> Demographic change has been recognised as a key determinant for explaining social change. Population changes are fairly predictable and the age transition can explain a wide range of socio-economic changes. For rural futures, demographic change is a key issue, since age structure in rural areas is often uneven and also unstable due to migration patterns. A number of policy related questions as well as research challenges are raised as a consequence.
    Keywords: demographic change; rural futures
    JEL: R11 R23
    Date: 2006–04

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.