nep-for New Economics Papers
on Forecasting
Issue of 2005‒08‒13
ten papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting with VARMA Models By Helmut Luetkepohl
  2. Assessing Forecast Performance in a VEC Model: An Empirical Examination By Zacharias Bragoudakis
  3. Why does the GARCH(1,1) model fail to provide sensible longer- horizon volatility forecasts? By Catalin Starica; Stefano Herzel; Tomas Nord
  4. No Predictable Components in G7 Stock Returns By Prasad Bidarkota; Khurshid M. Kiani
  5. Will the Euro Eventually Surpass the Dollar as Leading International Reserve Currency? By Menzie Chinn; Jeffrey Frankel
  6. Non-Linearities, Large Forecasters And Evidential Reasoning Under Rational Expectations By Ali al-Nowaihi; Sanjit Dhami
  7. Coping with Ageing: A Dynamic Approach to Quantify the Impact of Alternative Policy Options on Future Labour Supply in OECD Countries By Jean-Marc Burniaux; Romain Duval; Florence Jaumotte
  8. Forecasting the Professional Team Sporting Events: Evidence from Euro 2000 and 2004 Football Tournaments By Ferda HALICIOGLU
  9. Spatial Dependence, Housing Submarkets, and House Prices By Steven C. Bourassa; Eva Cantoni; Martin Hoesli
  10. Forecasting in Continuous Double Auction By Martin Smid

  1. By: Helmut Luetkepohl
    Abstract: Vector autoregressive moving-average (VARMA) processes are suitable models for producing linear forecasts of sets of time series variables. They provide parsimonious representations of linear data generation processes (DGPs). The setup for these processes in the presence of cointegrated variables is considered. Moreover, a unique or identified parameterization based on the echelon form is presented. Model specification, estimation, model checking and forecasting are discussed. Special attention is paid to forecasting issues related to contemporaneously and temporally aggregated processes.
    JEL: C32
    Date: 2004
  2. By: Zacharias Bragoudakis (Bank of Greece)
    Abstract: This paper is an exercise in applied macroeconomic forecasting. We examine the forecasting power of a vector error-correction model (VECM) that is anchored by a long-run equilibrium relationship between Greek national income and productive public expenditure as suggested by the economic theory. We compare the estimated forecasting values of the endogenous variables to the real-historical values using a stochastic simulation analysis. The simulation results provide new evidence supporting the ability of the model to forecast not only one-period ahead but also many periods into the future.
    Keywords: Cointegration, Forecasting, Simulation Analysis, Vector error- correction models
    JEL: C15 C32 C53 E0 E6
    Date: 2005–07–25
  3. By: Catalin Starica (Chalmers & Gothenburg University); Stefano Herzel (University of Perugia); Tomas Nord (Chalmers University of Technology)
    Abstract: The paper investigates from an empirical perspective aspects related to the occurrence of the IGARCH effect and to its impact on volatility forecasting. It reports the results of a detailed analysis of twelve samples of returns on financial indexes from major economies (Australia, Austria, Belgium, France, Germany, Japan, Sweden, UK, and US). The study is conducted in a novel, non-stationary modeling framework proposed in Starica and Granger (2005). The analysis shows that samples characterized by more pronounced changes in the unconditional variance display stronger IGARCH effect and pronounced differences between estimated GARCH(1,1) unconditional variance and the sample variance. Moreover, we document particularly poor longer-horizon forecasting performance of the GARCH(1,1) model for samples characterized by strong discrepancy between the two measures of unconditional variance. The periods of poor forecasting behavior can be as long as four years. The forecasting behavior is evaluated through a direct comparison with a naive non-stationary approach and is based on mean square errors (MSE) as well as on an option replicating exercise.
    Keywords: stock returns, volatility forecasting, GARCH(1,1), IGARCH effect, hedging, non-stationary, longer horizon forecasting
    JEL: C14 C32
    Date: 2005–08–02
  4. By: Prasad Bidarkota (Department of Economics, Florida International University); Khurshid M. Kiani (Department of Economics, Wilfrid Laurier University)
    Abstract: We search for time-varying predictable components in monthly excess stock index returns over the risk free rates in the G7 countries. The predictable components provide an estimate of the expected excess returns. Our unobserved components model improves on Conrad and Kaul (1988) by taking into account fat tails widely documented in returns data. Statistical hypotheses tests fail to reveal any significant time-varying predictable components in excess returns for any of the countries, except Canada. Our results are in sharp contrast to Conrad and Kaul (1988), who do isolate time-varying expected returns in weekly sizeweighted portfolio returns using the same methodology but in a Gaussian setting.
    Keywords: stock return predictability, unobserved components, fat tails, stable distributions
    JEL: C22 C53 G14
    Date: 2004–10
  5. By: Menzie Chinn; Jeffrey Frankel
    Abstract: Might the dollar eventually follow the precedent of the pound and cede its status as leading international reserve currency? Unlike ten years ago, there now exists a credible competitor: the euro. This paper econometrically estimates determinants of the shares of major currencies in the reserve holdings of the world’s central banks. Significant factors include: size of the home country, inflation rate (or lagged depreciation trend), exchange rate variability, and size of the relevant home financial center (as measured by the turnover in its foreign exchange market). We have not found that net international debt position is an important determinant. Network externality theories would predict a tipping phenomenon. Indeed we find that the relationship between currency shares and their determinants is nonlinear (which we try to capture with a logistic function, or else with a dummy “leader” variable for the largest country). But changes are felt only with a long lag (we estimate a weight on the preceding year’s currency share around .9). The advent of the euro interrupts the continuity of the historical data set. So we estimate parameters on pre-1999 data, and then use them to forecast the EMU era. The equation correctly predicts a (small) narrowing in the gap between the dollar and euro over the period 1999-2004. Whether the euro might in the future rival or surpass the dollar as the world’s leading international reserve currency appears to depend on two things: (1) do the United Kingdom and enough other EU members join euroland so that it becomes larger than the US economy, and (2) does US macroeconomic policy eventually undermine confidence in the value of the dollar, in the form of inflation and depreciation. What we learn about functional form and parameter values helps us forecast, contingent on these two developments, how quickly the euro might rise to challenge the dollar. Under two important scenarios the remaining EU members, including the UK, join EMU by 2020 or else the recent depreciation trend of the dollar persists into the future the euro may surpass the dollar as leading international reserve currency by 2022.
    JEL: F02 F31 F33
    Date: 2005–08
  6. By: Ali al-Nowaihi; Sanjit Dhami
    Abstract: Rational expectations is typically taken to mean that, conditional on the information set and the relevant economic theory, the expectation formed by an economic agent should be equal to its mathematical expectation. This is correct only when actual inflation is “linear” in the aggregate inflationary expectation or if it is non-linear then forecasters are “small” and use “causal reasoning”. We show that if actual in- flation is non-linear in expected inflation and (1) there are “large” forecasters, or, (2) small/ large forecasters who use “evidential reasoning”, then the optimal forecast does not equal the mathematical expectation of the variable being forecast. We also show that when actual inflation is non-linear in aggregate inflation there might be no solution if one identifies rational expectations with equating the expectations to the mathematical average, while there is a solution using the “correct” forecasting rule under rational expectations. Furthermore, results suggest that published forecasts of inflation may be systematically different from the statistical averages of actual inflation and output, on average, need not equal the natural rate. The paper has fundamental implications for macroeconomic forecasting and policy, testing the assumptions and implications of market efficiency and for rational expectations in general.
    Keywords: Non-linearities; large forecasters; evidential reasoning; rational expectations; endogenous forecasts; classical and behavioral game theory
    JEL: C53 D84 E47 E63
    Date: 2005–08
  7. By: Jean-Marc Burniaux; Romain Duval; Florence Jaumotte
    Abstract: <P>In the face of the substantial ageing of population expected to occur in OECD countries over coming decades, policies that boost labour-force participation attract considerable interest. There remain large cross-country divergences in participation rates that are largely accounted for by differences in participation of specific groups, in particular prime-age women, older workers and also youth. This suggests that policies targeting these groups could have important effects. The aim of this paper is to examine whether the potential impact of several policy reforms is able to attenuate or to offset the adverse trend in aggregate participation rates that would otherwise occur because of ageing population. It uses a simple dynamic modelling framework that generates longer-term projections of participation rates and labour supplies in OECD countries and alternative scenarios of policy reforms. The main outcome of this analysis is that the combined effect of possible reforms targeting ...</P> <P>Faire face au vieillissement : une approche dynamique pour mesurer l’impact d’alternatives politiques sur l’offre future de travail dans les pays de l’OCDE <P>Les pays de l’OCDE sont confrontés à un vieillissement important de leur population au cours des décades à venir et ceci explique le regain d’intérêt considérable pour les politiques susceptibles de stimuler la participation au marché du travail. Il subsiste des différences importantes de participation entre les pays de l’OCDE qui s’expliquent en grande partie par des différences de participation de groupes spécifiques, en particulier les femmes dans la force de l’âge, les travailleurs âgés et les jeunes. Ces différences suggèrent qu’il reste une marge de manoeuvre importante pour des réformes de politique économique visant ces groupes. Le but de ce papier est d’examiner si l’impact potentiel d’un certain nombre de réformes est susceptible d’atténuer, voire de compenser, la tendance future à la diminution des taux de participation agrégés telle qu’elle résulterait du vieillissement de la population. Cette analyse utilise un modèle dynamique simple qui génère des prévisions à long ...</P>
    Keywords: retraite, labor force and employment, retirement policies, Demographic Trends and Forecasts, Economics of Gender, Size and Structure, Retirement, Tendances et Prévisions Démographiques, Economie de l’Egalité des Sexes, Force de Travail et Emploi, Taille et Structure, Politiques des Retraites
    JEL: J11 J16 J21 J26
    Date: 2004–06–21
  8. By: Ferda HALICIOGLU (The University of Greenwich)
    Abstract: This study aims at predicting the most likely winners of international football tournaments. To this end, this paper employs a relatively simple statistical method, which is based on the seasonal coefficients of variation (CVs) of the end-of-season points from domestic football leagues to measure the degree of competitive balance and to use it as a comparative indicator between the contesting countries in international football tournaments. The seasonal CV values computed from over ten seasons of the top division final standings of participating countries of Euro 2000 and 2004 football tournaments were utilized to predict the outcome of these football tournaments. The results based on the short, mid and long-term seasonal CV values suggest that this forecasting approach provides significantly reliable results in the case of Euro 2000 but not in the case of Euro 2004.
    Keywords: Competitive balance, Football, Ranking, UEFA, Sports forecasts.
    JEL: L80 H50
    Date: 2005–08–01
  9. By: Steven C. Bourassa; Eva Cantoni; Martin Hoesli
    Abstract: This paper compares the impacts of alternative models of spatial dependence on the accuracy of house price predictions in a mass appraisal context. Explicit modeling of spatial dependence is characterized as a more fluid approach to defining housing submarkets. This approach allows the relevant “submarket” to vary from house to house and for transactions involving other dwellings in each submarket to have varying impacts depending on distance. We compare the predictive ability of different specifications of both geostatistical and lattice models as well as a simpler model based on submarkets with fixed boundaries. We conclude that – for our data – no spatial statistics method does as well in terms of predictive ability as a simple OLS model that includes a series of dummy variables defining submarkets. However, of the spatial statistics methods, geostatistical models provide more accurate predictions than lattice models. We argue that this is due to the fact that the kriging procedure used to make predictions in a geostatistical framework directly incorporates spatial information about nearby properties. That is not possible in a lattice framework due to the reliance on a matrix of weights that incorporates relationships only for the sample of properties that transact.
    Keywords: : spatial dependence; hedonic price models; geostatistical models; lattice models; mass appraisal; housing submarkets
    JEL: C21 R31
    Date: 2005–06
  10. By: Martin Smid (Institute of Information Theory & Automation of the Academy of Sciences of the Czech Republic)
    Abstract: Recently, the continuous double auction, i.e. the trading mechanism used in the majority of the financial markets, is the subject of an extensive study. In the present paper, a model of the continuous double auction with the completely random flow of the limit orders is studied. The main result of the paper is an approximate formula for the distribution of the market price and the traded volume at the time s given the information available at t < s.
    Keywords: limit order markets, continuous double auction, price and volume, forecasting, market microstructure
    JEL: C51 G10
    Date: 2005–08–02

This nep-for issue is ©2005 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.