nep-for New Economics Papers
on Forecasting
Issue of 2007‒01‒14
eighteen papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting volatility and volume in the Tokyo stock market : long memory, fractality and regime switching By Lux, Thomas; Kaizoji, Taisei
  2. Computational Intelligence in Exchange-Rate Forecasting By Andreas S. Andreou; George A. Zombanakis
  3. Can Panel Data Really Improve the Predictability of the Monetary Exchange Rate Model? By Westerlund, Joakim; Basher, Syed A.
  4. The Markov-Switching Multifractal Model of asset returns : GMM estimation and linear forecasting of volatility By Lux, Thomas
  5. Quantile Forecasts of Daily Exchange Rate Returns from Forecasts of Realized Volatility By Clements, Michael P.; Galvão, Ana Beatriz; Kim, Jae H.
  6. Transaction taxes, traders' behavior and exchange rate risks By Demary, Markus
  7. Forecasting Inflation in Developing Nations: The Case of Pakistan By Feridun, Mete
  9. Domestic and Global Determinants of the U.S. Inflation Expectations By Efrem Castelnuovo
  10. Can Fluctuations of Money (M2) Help Predict Future Fluctuations of Income (GDP)? An Empirical Investigation on Malaysian Data By Feridun, Mete
  11. Point and interval forecasting of wholesale electricity prices: Evidence from the Nord Pool market By Weron, Rafal; Misiorek, Adam
  12. Forecasting using a large number of predictors - Is Bayesian regression a valid alternative to principal components? By Christine De Mol; Domenico Giannone; Lucrezia Reichlin
  13. Regional Unemployment Forecasting Using Structural Component Models With Spatial Autocorrelation By Katharina Hampel; Marcus Kunz; Norbert Schanne; Ruediger Wapler; Antje Weyh
  14. A structural model for corporate profit in the U.S. industry By Gomez-Sorzano, Gustavo
  15. Variation principles for modeling in resource economics By Bazhanov, Andrei
  16. Territorial Scenarios for an Integrated Europe: Driving Forces of Change and Quantitative Forecasts By Roberta Capello; Barbara Chizzolini; Ugo Fratesi
  17. Sectoral and Industrial Business Cycles By Everts, Martin
  18. Fiscal Sustainability in Selected Transition Countries By Aristovnik, Aleksander; Berčič, Boštjan

  1. By: Lux, Thomas; Kaizoji, Taisei
    Abstract: We investigate the predictability of both volatility and volume for a large sample of Japanese stocks. The particular emphasis of this paper is on assessing the performance of long memory time series models in comparison to their short-memory counterparts. Since long memory models should have a particular advantage over long forecasting horizons, we consider predictions of up to 100 days ahead. In most respects, the long memory models (ARFIMA, FIGARCH and the recently introduced multifractal model) dominate over GARCH and ARMA models. However, while FIGARCH and ARFIMA also have quite a number of cases with dramatic failures of their forecasts, the multifractal model does not suffer from this shortcoming and its performance practically always improves upon the naïve forecast provided by historical volatility. As a somewhat surprising result, we also find that, for FIGARCH and ARFIMA models, pooled estimates (i.e. averages of parameter estimates from a sample of time series) give much better results than individually estimated models.
    Keywords: forecasting, long memory models, volume, volatility
    JEL: C22 C53 G12
    Date: 2006
  2. By: Andreas S. Andreou (University of Cyprus); George A. Zombanakis (Bank of Greece)
    Abstract: This paper applies computational intelligence methods to exchange rate forecasting. In particular, it employs neural network methodology in order to predict developments of the Euro exchange rate versus the U.S. Dollar and the Japanese Yen. Following a study of our series using traditional as well as specialized, non-parametric methods together with Monte Carlo simulations we employ selected Neural Networks (NNs) trained to forecast rate fluctuations. Despite the fact that the data series have been shown by the Rescaled Range Statistic (R/S) analysis to exhibit random behaviour, their internal dynamics have been successfully captured by certain NN topologies, thus yielding accurate predictions of the two exchange-rate series.
    Keywords: Exchange - rate forecasting, Neural networks
    JEL: C53
    Date: 2006–11
  3. By: Westerlund, Joakim; Basher, Syed A.
    Abstract: A common explanation for the inability of the monetary model to beat the random walk in forecasting future exchange rates is that conventional time series tests may have low power, and that panel data should generate more powerful tests. This paper provides an extensive evaluation of this power argument to the use of panel data in the forecasting context. In particular, by using simulations it is shown that although pooling of the individual prediction tests can lead to substantial power gains, pooling only the parameters of the forecasting equation, as has been suggested in the previous literature, does not seem to generate more powerful tests. The simulation results are illustrated through an empirical application.
    Keywords: Monetary Exchange Rate Model; Forecasting; Panel Data; Pooling; Bootstrap.
    JEL: F47 F31 C32 C15 C33
    Date: 2006–12–20
  4. By: Lux, Thomas
    Abstract: Multifractal processes have recently been proposed as a new formalism for modelling the time series of returns in ¯nance. The major attraction of these processes is their ability to generate various degrees of long memory in di®erent powers of returns - a feature that has been found in virtually all ¯nancial data. Initial di±culties stemming from non-stationarity and the combinatorial nature of the original model have been overcome by the introduction of an iterative Markov-switching multifractal model in Calvet and Fisher (2001) which allows for estimation of its parameters via maximum likelihood and Bayesian forecasting of volatility. However, applicability of MLE is restricted to cases with a discrete distribution of volatility components. From a practical point of view, ML also be- comes computationally unfeasible for large numbers of components even if they are drawn from a discrete distribution. Here we propose an alter- native GMM estimator together with linear forecasts which in principle is applicable for any continuous distribution with any number of volatility components. Monte Carlo studies show that GMM performs reasonably well for the popular Binomial and Lognormal models and that the loss incurred with linear compared to optimal forecasts is small. Extending the number of volatility components beyond what is feasible with MLE leads to gains in forecasting accuracy for some time series.
    Keywords: Markov-switching, multifractal, forecasting, volatility, GMM estimation
    JEL: C20 G12
    Date: 2006
  5. By: Clements, Michael P. (University of Warwick); Galvão, Ana Beatriz (Queen Mary, University of London); Kim, Jae H. (Monash University)
    Abstract: Quantile forecasts are central to risk management decisions because of the widespread use of Value-at-Risk. A quantile forecast is the product of two factors : the model used to forecast volatility, and the method of computing quantiles from the volatility forecasts. In this paper we calculate and evaluate quantile forecasts of the daily exchange rate returns of five currencies. The forecasting models that have been used in recent analyses of the predictability of daily realized volatility permit a comparison of the predictive power of different measures of intraday variation and intraday returns in forecasting exchange rate variability. The methods of computing quantile forecasts include making distributional assumptions for future daily returns as well as using the empirical distribution of predicted standardized returns with both rolling and recursive samples. Our main ?ndings are that the HAR model provides more accurate volatility and quantile forecasts for currencies which experience shifts in volatility, such as the Canadian dollar, and that the use of the empirical distribution to calculate quantiles can improve forecasts when there are shifts.
    Keywords: realized volatility ; quantile forecasting ; MIDAS ; HAR ; exchange rates
    JEL: C32 C53 F37
    Date: 2006
  6. By: Demary, Markus
    Abstract: We propose a new model of chartist-fundamentalist-interaction in which both groups of traders are allowed to select endogenously between different forecasting models and different investment horizons. Stochastic interest rates in both countries and different behavioral assumptions for trend-extrapolating and fundamental based forecasts determine the agents’ market orders which drive the exchange rate. A numerical analysis of the model shows that it is able to replicate stylized facts of observed financial return time series like excess kurtosis and volatility clustering. Within this framework we study the effects of transaction taxes on exchange rate volatil- ity and traders’ behavior measured by their population fractions. Simula- tions yield the result that on the macroscopic level these taxes reduce the variance of exchange rate returns, but also increase their kurtosis. Moreover, on the microscopic level the tax harms short-term speculation in favor of long-term investment, while it also harms trading rules based on economic fundamentals in favor to trend extrapolating trading rules.
    Keywords: Chartist-Fu e ist-Interaction, Exchange Rates, Financial Market Volatility, Tra tion Taxes
    Date: 2006
  7. By: Feridun, Mete
    Abstract: This study attempts to outline the practical steps which need to be undertaken to use autoregressive integrated moving average (ARIMA) time series models for forecasting Pakistan’s inflation. A framework for ARIMA forecasting is drawn up. On the basis of insample and out-of-sample forecast it can be concluded that the model has sufficient predictive powers and the findings are well in line with those of other studies. Further, in this study, the main focus is to forecast the monthly inflation on short-term basis, for this purpose, different ARIMA models are used and the candid model is proposed. On the basis of various diagnostic and selection & evaluation criteria the best and accurate model is selected for the short term forecasting of inflation.
    Keywords: Forecasting inflation; ARIMA
    JEL: E10
    Date: 2006
  8. By: Feridun, Mete
    Abstract: This article aims at modeling and forecasting inflation in Pakistan. For this purpose a number of econometric approaches are implemented and their results are compared. In ARIMA models, adding additional lags for p and/or q necessarily reduced the sum of squares of the estimated residuals. When a model is estimated using lagged variables, some observations are lost. Results further indicate that the VAR models do not perform better than the ARIMA (2, 1, 2) models and, the two factor model with ARIMA (2, 1, 2) slightly performs better than the ARIMA (2, 1, 2). Although the study focuses on the problem of macroeconomic forecasting, the empirical results have more general implications for small scale macroeconometric models.
    Keywords: Modeling and forecasting inflation; ARIMA; VAR.
    JEL: G1
    Date: 2006
  9. By: Efrem Castelnuovo (University of Padua)
    Abstract: This paper estimates a reduced-form model for the short-term U.S. inflation expectations and assesses the empirical relevance of the role played by some proxies of the business cycle in shaping forecasters’ projections. In particular, we consider both standard indicators of the "domestic" economic slack (such as the U.S. output and unemployment gap) and "global" measures of the business cycle (their G7 counterparts). Two main findings stand out. First, all the measures of economic slack we take into account turn out to be statistically significant when considered one at a time. Second, horserace regressions contrasting domestic and global measures of economic slack favors the latter, i.e. when global indicators are considered, domestic indicators take the wrong sign and lose their significance. These results are robust to the introduction of several additional indicators of inflationary pressures in the empirical model. Rolling regressions confirm our findings also at a subsample level. Overall, our results suggest that further research is needed for better understanding the role played by measures of the international economic slack in predicting the U.S. inflation expectations.
    Keywords: inflation expectations, output gap, unemployment gap, domestic factors, global factors
    JEL: F02 E31 E52 E58 F41
    Date: 2006–12
  10. By: Feridun, Mete
    Abstract: The paper aims at establishing whether the fluctuations of money help predict future fluctuations of income, that are not already predictable on the basis of fluctuations of income itself or other readily observable variables. For this purpose vector autoregression (VAR) modelling is used to test whether changes in money supply (M2) has any deterministic or predictive content for movements in Income (GDP). The analysis is performed using quarterly macroeconomic data from Malaysia spanning the period between 1980 and 2001. The results suggest that money (M2) and interest rates have information content for future movements in real GDP beyond that contained in past values of GDP itself. This relationship only establishes itself with a fairly long lag. The finding suggests the possibility of making use of the money-income relationship for forecasting purposes.
    Keywords: Vector autoregression (VAR); cointegration; causality
    JEL: A20
    Date: 2006
  11. By: Weron, Rafal; Misiorek, Adam
    Abstract: In this paper we assess the short-term forecasting power of different time series models in the Nord Pool electricity spot market. We evaluate the accuracy of both point and interval predictions; the latter are specifically important for risk management purposes where one is more interested in predicting intervals for future price movements than simply point estimates. We find evidence that non-linear regime-switching models outperform their linear counterparts and that the interval forecasts of all models are overestimated in the relatively non-volatile periods.
    Keywords: Wholesale electricity price; Point forecast; Interval forecast; AR model; Threshold AR model
    JEL: L94 Q40 C53 C22
    Date: 2006
  12. By: Christine De Mol (Universite Libre de Bruxelles – ECARES, Av. F. D. Roosevelt, 50 – CP 114, 1050 Bruxelles, Belgium.); Domenico Giannone (Universite Libre de Bruxelles – ECARES, Av. F. D. Roosevelt, 50 – CP 114, 1050 Bruxelles, Belgium.); Lucrezia Reichlin (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.)
    Abstract: This paper considers Bayesian regression with normal and doubleexponential priors as forecasting methods based on large panels of time series. We show that, empirically, these forecasts are highly correlated with principal component forecasts and that they perform equally well for a wide range of prior choices. Moreover, we study the asymptotic properties of the Bayesian regression under Gaussian prior under the assumption that data are quasi collinear to establish a criterion for setting parameters in a large cross-section. JEL Classification: C11,C13, C33, C53.
    Keywords: Bayesian VAR, ridge regression, Lasso regression, principal components, large cross-sections.
    Date: 2006–12
  13. By: Katharina Hampel; Marcus Kunz; Norbert Schanne; Ruediger Wapler; Antje Weyh
    Abstract: Labour-market policies are increasingly being decided on a regional level. This implies that institutions have an increased need for regional forecasts as a guideline for their decision-making process. Therefore, we forecast regional unemployment in the 176 German labour market districts. We use an augmented structural component (SC) model and compare the results from this model with those from basic SC and autoregressive integrated moving average (ARIMA) models. Basic SC models lack two important dimensions: First, they only use level, trend, seasonal and cyclical components, although former periods of the dependent variable generally have a significant influence on the current value. Second, as spatial units become smaller, the influence of “neighbour-effects†becomes more important. In this paper we augment the SC model for structural breaks, autoregressive components and spatial autocorrelation. Using unemployment data from the Federal Employment Services in Germany for the period December 1997 to August 2005, we first estimate basic SC models with components for structural breaks and ARIMA models for each spatial unit separately. In a second stage, autoregressive components are added into the SC model. Third, spatial autocorrelation is introduced into the SC model. We assume that unemployment in adjacent districts is not independent for two reasons: One source of spatial autocorrelation may be that the effect of certain determinants of unemployment is not limited to the particular district but also spills over to neighbouring districts. Second, factors may exist which influence a whole region but are not fully captured by exogenous variables and are reflected in the residuals. We test the quality of the forecasts from the basic models and the augmented SC model by ex-post-estimation for the period September 2004 to August 2005. First results show that the SC model with autoregressive elements and spatial autocorrelation is superior to basic SC and ARIMA models in most of the German labour market districts.
    Date: 2006–08
  14. By: Gomez-Sorzano, Gustavo
    Abstract: I estimate a theoretically and statistically satisfying model to account for corporate profit represented by Net Rental Income (NRI) for one of the largest Real Estate Investment Trust companies (REIT) in the U.S. I claim that I have found an accurate method to forecasts the direction and dollar amount of corporate profit in the apartment industry in The U.S. that can be extended to the remaining branches of the U.S. industry. The variables that together account for ninety seven percent of the variation in NRI for this apartment company are, one-period time lag of lease renewals, the Federal Funds interest rate end of month, total gross potential of the company, total concessions, two-period time lag of move-ins, the ratio between total non-farm employment and total construction permits authorized, the inventory of houses in the U.S, one-period time lag of move-outs and this REIT apartment units occupied.
    Keywords: REIT; Corporate Profit; Net Rental Income (NRI); demand for lease renewals
    JEL: C53 D41 C32 C51 L11 D21
    Date: 2006–05–07
  15. By: Bazhanov, Andrei
    Abstract: A technique for the construction of the model of nonrenewable resources depletion is offered. The approach is based on the assumption of the fulfillment of a variation principle. The model adequacy is examined with respect to world oil extraction data from 1859 to 2005. The possibilities of the use of the model in forecasting problems and in construction of the path of extraction, satisfying the intergenerational justice principle are discussed. Empirical justification of the hypothesis of the fulfillment of the Hamilton principle in resource economics gives an opportunity of the use of some laws of mechanics in economics.
    Keywords: nonrenewable resource; variation principle; intergenerational justice
    JEL: C63 Q32
    Date: 2005–08–08
  16. By: Roberta Capello; Barbara Chizzolini; Ugo Fratesi
    Abstract: The paper presents the second step of an ambitious research project, which has the aim to provide territorial scenarios of the New Europe in 15 years, developed under different hypotheses on the most important driving forces of change in the fields of economy, demographic, society, technology and institutions. The first step was presented last year at the ERSA conference in Amsterdam. In that occasion, the paper dealt with the econometric model (labelled MASST – Macroeconomic, social, sectoral and territorial model) built for the forecasting activity, presenting its strengths and weaknesses and the main results obtained by the estimates of the model. In this paper the additional work is presented, and the main conceptual and methodological steps forward analysed. In particular, the aims of the paper are the following: - to present the main driving forces that influence the future of Europe and of its territory. These are of different nature: socio-cultural (future migration forces and future birth and death rates), institutional (deepening vs. widening of enlargement), macroeconomic (trend in the euro/$ exchange rate, trend in fiscal morality – i.e. trend in public debts, revision of the Maastricht parameters -, trend in interest rates, trend in inflation rate, geo-political orientation of FDI, rebalancing of external accounts of big emerging countries; increase in energy price), political (reforms of the structural funds and of the Community Agricultural Policy); - to present the different hypotheses under which the scenarios are built. The idea is to build three scenarios, a baseline scenario, a competitive and a cohesive scenario, and to present the differences among them; - to present the results of the simulation. The MASST model is able to provide both regional GDP growth rates and GDP levels, as well as regional population growth rates, and population levels, for the three scenarios. The model is able to provide the simulations for 27 Countries (the old 15 EU members, the new 10 Countries and Bulgaria and Romania) and for their 259 regions.
    Date: 2006–08
  17. By: Everts, Martin
    Abstract: This article calculates the sectoral and industrial business cycles by means of the band-pass filters by Baxter and King (1999) and Christiano and Fitzgerald (2003), to subsequently analyze the correlations between the sectors and industries and the overall economy. It can be shown that the correlations between the business cycles of the sectors and industries and the overall economy differ strongly. The agriculture sector and the industries mining and quarrying, electricity and education for example exhibit almost no correlation with the overall economy; The wholesale and retail as well as the transport industry on the other hand have a high correlation. By means of an analysis of the leading and lagging correlations it can be shown that the wholesale and retail industry leads the overall economy by two quarters. Thus, the wholesale and retail industry can be used as an indicator for the development of the overall economy.
    Keywords: Business Cycle; Correlation; Band-Pass Filter; Sectoral Cycles; Industrial Cycles; Cross-Country Correlation; Monetary Policy; Forecasting
    JEL: E37 E32
    Date: 2006–06
  18. By: Aristovnik, Aleksander; Berčič, Boštjan
    Abstract: In the article, we review recent literature on fiscal sustainability with particular reference to problems that are specific to transition countries. While the original literature on fiscal sustainability is chiefly focused on industrial countries there are by now few works that have focused on fiscal sustainability in transition countries. Consequently, the article’s purpose is to assess the short-, medium- and long-term sustainability of fiscal policy (under set assumptions) on the national level in the great majority of transition countries which we divide into three main groups, i.e. Central and Eastern Europe (CEE), Southern and Eastern Europe (SEE) and the Commonwealth of Independent States (CIS). Based on simple mainstream theory measures of fiscal sustainability, the results indicate that fiscal sustainability seems to be a problem in many transition countries, particularly in CEE (e.g. Czech Republic, Hungary, and Poland) and the SEE region (e.g. Albania and Croatia).
    Keywords: transition; public sector; fiscal policy; sustainability; forecasting
    JEL: E17 H62 H00
    Date: 2007–01

This nep-for issue is ©2007 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.