New Forecasting Papers 2011-03-07

In this issue we have Forecasting breaks and forecasting during breaks, Forecasting With Many Predictors: An Empirical Comparison, Multivariate High-Frequency-Based Volatility (HEAVY) Models, The forecasting horizon of inflationary expectations and perceptions in the EU, and more.

  1. Forecasting breaks and forecasting during breaks
    Date: 2011
    By: Jennifer L. Castle
    Nicholas W.P. Fawcett
    David F. Hendry
    Success in accurately forecasting breaks requires that they are predictable from relevant information available at the forecast origin using an appropriate model form, which can be selected and estimated before the break. To clarify the roles of these six necessary conditions, we distinguish between the information set for ‘normal forces’ and the ones for ‘break drivers’, then outline sources of potential information. Relevant non-linear, dynamic models facing multiple breaks can have more candidate variables than observations, so we discuss automatic model selection. As a failure to accurately forecast breaks remains likely, we augment our strategy by modelling breaks during their progress, and consider robust forecasting devices.
    Keywords: Economic forecasting, structural breaks, information sets, non-linearity
    JEL: C1
  2. Forecasting With Many Predictors. An Empirical Comparison
    Date: 2011-02-17
    By: Eliana González
    Three methodologies of estimation of models with many predictors are implemented to forecast Colombian inflation. Two factor models, based on principal components, and partial least squares, as well as a Bayesian regression, known as Ridge regression are estimated. The methodologies are compared in terms of out-sample RMSE relative to two benchmark forecasts, a random walk and an autoregressive model. It was found, that the models that contain many predictors outperformed the benchmarks for most horizons up to 12 months ahead, however the reduction in RMSE is only statistically significant for the short run. Partial least squares outperformed the other approaches based on large datasets.
  3. Multivariate High-Frequency-Based Volatility (HEAVY) Models
    Date: 2011
    By: Diaa Noureldin
    Neil Shephard
    Kevin Sheppard
    This paper introduces a new class of multivariate volatility models that utilizes high-frequency data. We discuss the models’ dynamics and highlight their differences from multivariate GARCH models. We also discuss their covariance targeting specification and provide closed-form formulas for multi-step forecasts. Estimation and inference strategies are outlined. Empirical results suggest that the HEAVY model outperforms the multivariate GARCH model out-of-sample, with the gains being particularly significant at short forecast horizons. Forecast gains are obtained for both forecast variances and correlations.
    Keywords: HEAVY model, GARCH, multivariate volatility, realized covariance, covariance targeting, multi-step forecasting, Wishart distribution
    JEL: C32
  4. The forecasting horizon of inflationary expectations and perceptions in the EU – Is it really 12 months?
    Date: 2010-12
    By: Lars Jonung
    Staffan Linden
    We use survey based inflationary expectations to explore the forecasting horizons implicitly used by the respondents to questions about the expected rate of inflation during the coming 12 months. We examine the forecast errors, the mean error and the RMSEs, to study if the forecast horizon is truly 12 months as implied by the questionnaires. Our working hypothesis is that the forecast error has a U-shaped pattern, reaching its lowest value on the 12-month horizon. Our exploratory study reveals large differences across countries. For most countries, we get the expected U-shaped outcome for the forecast errors. The horizon implicitly used by respondents when answering the questions is not related to the explicit time horizon of the questionnaire. On average respondents use the same horizon when answering both questions.
    JEL: C33
  5. MOSES: Model of Swedish Economic Studies
    Date: 2011-01-01
    By: Bårdsen, Gunnar (Department of Economics)
    den Reijer, Ard (Monetary Policy Department, Central Bank of Sweden)
    Jonasson, Patrik (Monetary Policy Department, Central Bank of Sweden)
    Nymoen, Ragnar (Department of Economics)
    MOSES is an aggregate econometric model for Sweden, estimated on quarterly data, and intended for short-term forecasting and policy simulations. After a presentation of qualitative model properties, the econometric methodology is summarized. The model properties, within sample simulations, and examples of dynamic simulation (model forecasts) for the period 2009q2-2012q4 are presented. We address practical issues relating to operational use and maintenance of a macro model of this type. The detailed econometric equations are reported in an appendix.
    Keywords: macroeconomic model; policy analysis; general-to-specific modelling
    JEL: E12
  6. An Identification-Robust Test for Time-Varying Parameters in the Dynamics of Energy Prices
    Date: 2011-02-01
    By: Marie-Claude Beaulieu
    Jean-Marie Dufour
    Lynda Khalaf
    Maral Kichian
    We test for the presence of time-varying parameters (TVP) in the long-run dynamics of energy prices for oil, natural gas and coal, within a standard class of mean-reverting models. We also propose residual-based diagnostic tests and examine out-of-sample forecasts. In-sample LR tests support the TVP model for coal and gas but not for oil, though companion diagnostics suggest that the model is too restrictive to conclusively fit the data. Out-of-sample analysis suggests a randomwalk specification for oil price, and TVP models for both real-time forecasting in the case of gas and long-run forecasting in the case of coal

    Keywords: structural change, time-varying parameter, energy prices, coal, gas, crude oil, unidentified nuisance parameter, exact test, Monte Carlo test, Kalman filter, normality test,
    JEL: C22
  7. Nowcasting Business Cycles Using Toll Data
    Date: 2011-02
    By: Askitas, Nikos (IZA)
    Zimmermann, Klaus F. (IZA and University of Bonn)
    Nowcasting has been a challenge in the recent economic crisis. We introduce the Toll Index, a new monthly indicator for business cycle forecasting and demonstrate its relevance using German data. The index measures the monthly transportation activity performed by heavy transport vehicles across the country and has highly desirable availability properties (insignificant revisions, short publication lags) as a result of the innovative technology underlying its data collection. It is coincident with production activity due to the prevalence of just-in-time delivery. The Toll Index is a good early indicator of production as measured for instance by the German Production Index, provided by the German Statistical Office, which is a well-known leading indicator of the Gross National Product. The proposed new index is an excellent example of technological, innovation-driven economic telemetry, which we suggest should be established more around the world.
    Keywords: production forecasting, transportation, new products, macroeconomic forecasting, evaluating forecasts, data mining, business cycles, nowcasting, telemetry
    JEL: C82
  8. Predicting Output and Inflation in Less Developed Financial Markets Using the Yield Curve: Evidence from Malaysia
    Date: 2011-01-01
    By: Abdul Majid, Muhamed Zulkhibri
    This paper investigates the role of the term spread to predict domestic output and inflation in less developed financial market with the focus on Malaysia bond market. By controlling for past values of the dependent variable, this paper finds that the term spread of various bond maturities contain relevant information about future output and inflation at short horizons. Besides that, we employ a probit model to assess the ability for the yield curve to predict future economic slowdown. The results suggest that the term spread has contributed significantly in the probability of predicting future economic slowdown. Despite the under-developed bond market, the findings point to the potential for bond yields to play a greater role in monetary analysis beyond conventional indicators. From the policy point of views, the results from our analysis suggest that there is a significant potential for incorporating more technical and model based approaches using the yield curve beyond the usual indicator analysis.
    Keywords: Term spread; Forecasting; Monetary Policy; Malaysia
    JEL: E43
  9. The portfolio balance effect and reserve diversification: an empirical analysis
    Date: 2010-12
    By: Costas Karfakis
    The purpose of this study is to examine whether the portfolio balance effect, operating through the outstanding debts of US and euro area, and the signaling effect of sterilized intervention, operating through the relative composition of official reserves of developing and emerging countries, explain the developments of the euro/dollar exchange rate. The empirical analysis reveals that both effects are statistically significant and have the correct signs. The Clark-West testing procedure indicates that the model which relates the exchange rate to official reserves and the interest rate differential outperforms the random walk model in the forecasting accuracy.
  10. Monetary Policy Analysis in Real-Time. Vintage combination from a real-time dataset
    Date: 2011-02-20
    By: Carlo Altavilla (University of Naples Parthenope and CSEF)
    Matteo Ciccarelli (European Central Bank)
    This paper explores the role that the imperfect knowledge of the structure of the economy plays in the uncertainty surrounding the effects of rule-based monetary policy on unemployment dynamics in the euro area and the US. We employ a Bayesian model averaging procedure on a wide range of models which differ in several dimensions to account for the uncertainty that the policymaker faces when setting the monetary policy and evaluating its effect on real economy. We find evidence of a high degree of dispersion across models in both policy rule parameters and impulse response functions. Moreover, monetary policy shocks have very similar recessionary effects on the two economies with a different role played by the participation rate in the transmission mechanism. Finally, we show that a policy maker who does not take model uncertainty into account and selects the results on the basis of a single model may come to misleading conclusions not only about the transmission mechanism, but also about the differences between the euro area and the US, which are on average essentially small.
    Keywords: Monetary policy, Taylor rule, Real-time data, Great Moderation, Forecasting.
    JEL: E52
  11. ADOPT: a tool for predicting adoption of agricultural innovations
    Date: 2011
    By: Kuehne, G
    Llewellyn, Rick S.
    Pannell, D
    Wilkinson, R
    Dolling, P
    Ewing, M
    A wealth of evidence exists about the adoption of new practices and technologies in agriculture but there does not appear to have been any attempt to simplify this vast body of research knowledge into a model to make quantitative predictions across a broad range of contexts. This is despite increasing demand from research, development and extension agencies for estimates of likely extent of adoption and the likely timeframes for project impacts. This paper reports on the reasoning underpinning the development of ADOPT (Adoption and Diffusion Outcome Prediction Tool). The tool has been designed to: 1) predict an innovationâs likely peak extent of adoption and likely time for reaching that peak; 2) encourage users to consider the influence of a structured set of factors affecting adoption; and 3) engage R, D & E managers and practitioners by making adoptability knowledge and considerations more transparent and understandable. The tool is structured around four aspects of adoption: 1) characteristics of the innovation, 2) characteristics of the population, 3) actual advantage of using the innovation, and 4) learning of the actual advantage of the innovation. The conceptual framework used for developing ADOPT is described.
    Keywords: Adoption, Diffusion, Prediction, Research and Development/Tech Change/Emerging Technologies,

Taken from the NEP-FOR mailing list edited by Rob Hyndman.