nep-for New Economics Papers
on Forecasting
Issue of 2012‒09‒30
eleven papers chosen by
Rob J Hyndman
Monash University

  1. Comment on "Taylor rule exchange rate forecasting during the financial crisis" By Michael W. McCracken
  2. Adaptive forecasting in the presence of recent and ongoing structural change By Giraitis, L.; Kapetanios, G.; Price, S.
  3. Over-Optimistic Official Forecasts in the Eurozone and Fiscal Rules By Frankel, Jeffrey A.; Schreger, Jesse
  4. Fiscal forecast errors: governments vs independent agencies? By Rossana Merola; Javier J. Pérez
  5. Inflation forecasting using dynamic factor analysis. SAS 4GL programming approach By Adam Jêdrzejczyk
  6. Prediction for the 2012 United States Presidential Election using Multiple Regression Model By Sinha, Pankaj; Sharma, Aastha; Singh, Harsh Vardhan
  7. Performance Analysis of Hybrid Forecasting Model In Stock Market Forecasting By Mahesh S. Khadka; K. M. George; N. Park
  8. Design and Evaluation of Empirical Models for Stock Price Prediction By De Fortuny E.J.; De Smedt T.; Martens D.; Daelemans W.
  9. Will technological progress be sufficient to stabilize CO2 emissions from air transport in the mid-term? By Benoît Chèze; Julien Chevallier; Pascal Gastineau
  10. Testing for Predictability in a Noninvertible ARMA Model By Markku Lanne; Mika Meitz; Pentti Saikkonen
  11. Nonparametric Predictive Regression By Ioannis Kasparis; Elena Andreou; Peter C. B. Phillips

  1. By: Michael W. McCracken
    Abstract: In this note we discuss the paper on exchange rate forecasting by Molodtsova> and Papell (2012). In particular we discuss issues related to forecast origins and forecast> horizons when higher frequency exchange rate movements are predicted using lower> frequency quarterly macroaggregates.
    Keywords: Foreign exchange rates ; Taylor's rule
    Date: 2012
  2. By: Giraitis, L.; Kapetanios, G.; Price, S.
    Abstract: We consider time series forecasting in the presence of ongoing structural change where both the time series dependence and the nature of the structural change are unknown. Methods that downweight older data, such as rolling regressions, forecast averaging over different windows and exponentially weighted moving averages, known to be robust to historical structural change, are found to be also useful in the presence of ongoing structural change in the forecast period. A crucial issue is how to select the degree of downweighting, usually defined by an arbitrary tuning parameter. We make this choice data dependent by minimizing forecast mean square error, and provide a detailed theoretical analysis of our proposal. Monte Carlo results illustrate the methods. We examine their performance on 191 UK and US macro series. Forecasts using data-based tuning of the data discount rate are shown to perform well.
    Date: 2012
  3. By: Frankel, Jeffrey A. (Harvard University); Schreger, Jesse (Harvard University)
    Abstract: Why do countries find it so hard to get their budget deficits under control? Systematic patterns in the errors that official budget agencies make in their forecasts may play an important role. Although many observers have suggested that fiscal discipline can be restored via fiscal rules such as a legal cap on the budget deficit, forecasting bias can defeat such rules. The members of the eurozone are supposedly constrained by the fiscal caps of the Stability and Growth Pact. Yet ever since the birth of the euro in 1999, members have postponed painful adjustment by making overly optimistic forecasts of future growth and budget positions and arguing that the deficits will fall below the cap within a year or two. The new fiscal compact among the euro countries is supposed to make budget rules more binding by putting them into laws and constitutions at the national level. But what is the record with such national rules? Our econometric findings are summarized as follows: -Governments' budget forecasts are biased in the optimistic direction, especially among the Eurozone countries, especially when they have large contemporaneous budget deficits, and especially during booms. -Governments' real GDP forecasts are similarly over-optimistic during booms. -Despite the well-known tendency of eurozone members to exceed the 3% cap on budget deficits, often in consecutive years, they almost never forecast that they will violate the cap in the coming years. This is the source of the extra bias among eurozone forecasts. If euro area governments are not in violation of the 3% cap at the time forecasts are made, forecasts are no more biased than other countries. -Although euro members without national budget balance rules have a larger over-optimism bias than non-member countries, national fiscal rules help counteract the wishful thinking that seems to come with euro membership. The reason is that when governments are in violation of the 3% cap the national rules apparently constrain them from making such unrealistic forecasts. -Similarly, the existence of an independent fiscal institution producing budget forecasts at the national level reduces the over-optimism bias of forecasts made when the countries are in violation of the 3% cap.
    JEL: E62 H20
    Date: 2012–09
  4. By: Rossana Merola (OECD); Javier J. Pérez (Banco de España)
    Abstract: The fact that the literature tends to find optimistic biases in national fiscal projections has led to a growing recognition in the academic and policy arenas of the need for independent forecasts in the fiscal domain, prepared by independent agencies, such as the European Commission in the case of Europe. Against this background the aim of this paper is to test: (i) whether the forecasting performance of governments is indeed worse than that of international organizations, and (ii) whether fiscal projections prepared by international organizations are free from political economy distortions. The answer to these both questions is no: our results, based on real-time data for 15 European countries over the period 1999-2007, point to the rejection of the two hypotheses under scrutiny. We motivate the empirical analysis on the basis of a model in which an independent agency tries to minimize the distance to the government forecast. Starting from the assumption that the government’s information set includes private information not available to outside forecasters, we show how such a framework can help in understanding the observed empirical evidence
    Keywords: forecast errors, fi scal policies, fi scal forecasting, political economy
    JEL: H6 E62 C53
    Date: 2012–09
  5. By: Adam Jêdrzejczyk (Warsaw School of Economics)
    Abstract: The purpose of this article is to introduce an original macro code written in SAS 4GL. This macro is used to automate the process of forecasting with dynamic factor analysis. Automation of the process helps to save significant amounts of time and effort for the researcher. It also enables to compare different model specifications directly and, hence, to make conclusions that would be imperceptible without such automation, which is shown on the empirical study example.
    Keywords: statistical programming, forecasting, factor models, inflation
    JEL: C22 C53 C80 E31
    Date: 2012–09–16
  6. By: Sinha, Pankaj; Sharma, Aastha; Singh, Harsh Vardhan
    Abstract: This paper investigates the factors responsible for predicting 2012 U.S. Presidential election. Though contemporary discussions on Presidential election mention that unemployment rate will be a deciding factor in this election, it is found that unemployment rate is not significant for predicting the forthcoming Presidential election. Except GDP growth rate, various other economic factors like interest rate, inflation, public debt, change in oil and gold prices, budget deficit/surplus and exchange rate are also not significant for predicting the U.S. Presidential election outcome. Lewis-Beck and Rice (1982) proposed Gallup rating, obtained in June of the election year, as a significant indicator for forecasting the Presidential election. However, the present study finds that even though there exists a relationship between June Gallup rating and incumbent vote share in the Presidential election, the Gallup rating cannot be used as the sole indicator of the Presidential elections. Various other non-economic factors like scandals linked to the incumbent President and the performance of the two parties in the midterm elections are found to be significant. We study the influence of the above economic and non-economic variables on voting behavior in U.S. Presidential elections and develop a suitable regression model for predicting the 2012 U.S. Presidential election. The emergence of new non-economic factors reflects the changing dynamics of U.S. Presidential election outcomes. The proposed model forecasts that the Democrat candidate Mr. Barack Obama is likely to get a vote percentage between 51.818 % - 54.239 %, with 95% confidence interval.
    Keywords: USA Presidential election; forecasting; regression; Gallup rating; Congress; Scandal;macroeconomic variable; midterm election;
    JEL: C53 C5 E17 D72 C01 C2
    Date: 2012–08–05
  7. By: Mahesh S. Khadka; K. M. George; N. Park
    Abstract: This paper presents performance analysis of hybrid model comprise of concordance and Genetic Programming (GP) to forecast financial market with some existing models. This scheme can be used for in depth analysis of stock market. Different measures of concordances such as Kendalls Tau, Ginis Mean Difference, Spearmans Rho, and weak interpretation of concordance are used to search for the pattern in past that look similar to present. Genetic Programming is then used to match the past trend to present trend as close as possible. Then Genetic Program estimates what will happen next based on what had happened next. The concept is validated using financial time series data (S&P 500 and NASDAQ indices) as sample data sets. The forecasted result is then compared with standard ARIMA model and other model to analyse its performance.
    Date: 2012–09
  8. By: De Fortuny E.J.; De Smedt T.; Martens D.; Daelemans W.
    Abstract: The efficiënt market hypothesis and related theories claim that it is impossible to predict future stock prices. Even so, empirical research has countered this claim by achieving better than random prediction performance. Using a model built from a combination of text mining and time series prediction, we provide further evidence to counter the efficient market hypothesis. We discuss the difficulties in evaluating such models by investigating the drawbacks of the common choices of evaluation metrics used in these empirical studies. We continue by suggesting alternative techniques to validate stock prediction models, circumventing these shortcomings. Finally, a trading system is built for the Euronext Brussels stock exchange market. In our framework, we applied a novel sentiment mining technique in the design of the model and show the usefulness of state-of-the-art explanation-based techniques to validate the resulting models.
    Date: 2012–09
  9. By: Benoît Chèze; Julien Chevallier; Pascal Gastineau
    Abstract: This article investigates whether anticipated technological progress can be expected to be strong enough to offset carbon dioxide (CO2) emissions resulting from the rapid growth of air transport. Aviation CO2 emissions projections are provided at the worldwide level and for eight geographical zones until 2025. Total air traffic flows are first forecast using a dynamic panel-data econometric model, and then converted into corresponding quantities of air traffic CO2 emissions using specific hypotheses and energy factors. None of our nine scenarios appears compatible with the objective of 450 ppm CO2-eq. (a.k.a. "scenario of type I") recommended by the Intergovernmental Panel on Climate Change (IPCC). None is either compatible with the IPCC scenario of type III, which aims at limiting global warming to 3.2°C.
    Keywords: Air transport; CO2 emissions; Forecasting; Climate change
    JEL: C53 L93 Q47 Q54
    Date: 2012
  10. By: Markku Lanne (Department of Political and Economic Studies, University of Helsinki); Mika Meitz (Department of Economics, Koç University); Pentti Saikkonen (Department of Mathematics and Statistics, University of Helsinki)
    Abstract: We develop likelihood-based tests for autocorrelation and predictability in a first order non-Gaussian and noninvertible ARMA model. Tests based on a special case of the general model, referred to as an all-pass model, are also obtained. Data generated by an all-pass process are uncorrelated but, in the non-Gaussian case, dependent and nonlinearly predictable. Therefore, in addition to autocorrelation the proposed tests can also be used to test for nonlinear predictability. This makes our tests different from their previous counterparts based on conventional invertible ARMA models. Unlike in the invertible case, our tests can also be derived by standard methods that lead to chi-squared or standard normal limiting distributions. A further convenience of the noninvertible ARMA model is that, to some extent, it can allow for conditional heteroskedasticity in the data which is useful when testing for predictability in economic and financial data. This is also illustrated by our empirical application to U.S. stock returns, where our tests indicate the presence of nonlinear predictability.
    Keywords: Non-Gaussian time series, noninvertible ARMA model, all-pass process.
    JEL: C58 G12
    Date: 2012–09
  11. By: Ioannis Kasparis; Elena Andreou; Peter C. B. Phillips
    Abstract: A unifying framework for inference is developed in predictive regressions where the predictor has unknown integration properties and may be stationary or nonstationary. Two easily implemented nonparametric F-tests are proposed. The test statistics are related to those of Kasparis and Phillips (2012) and are obtained by kernel regression. The limit distribution of these predictive tests holds for a wide range of predictors including stationary as well as non-stationary fractional and near unit root processes. In this sense the proposed tests provide a unifying framework for predictive inference, allowing for possibly nonlinear relationships of unknown form, and offering robustness to integration order and functional form. Under the null of no predictability the limit distributions of the tests involve functionals of independent ÷² variates. The tests are consistent and divergence rates are faster when the predictor is stationary. Asymptotic theory and simulations show that the proposed tests are more powerful than existing parametric predictability tests when deviations from unity are large or the predictive regression is nonlinear. Some empirical illustrations to monthly SP500 stock returns data are provided.
    Keywords: Functional regression, Nonparametric predictability test, Nonparametric regression, Stock returns, Predictive regression
    Date: 2012–09

This nep-for issue is ©2012 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.