nep-for New Economics Papers
on Forecasting
Issue of 2012‒04‒03
eleven papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting from Structural Econometric Models By David F. Hendry; Grayham E. Mizon
  2. Short-term forecasting of the Japanese economy using factor models By Claudia Godbout; Marco J. Lombardi
  3. Empirical analysis of the forecast error impact of classical and bayesian beta adjustment techniques By Sinha, Pankaj; Jayaraman, Prabha
  4. Informational Efficiency of the EU ETS market ? a study of price predictability and profitable trading By Kimmo Ollikka; Piia Aatola; Markku Ollikainen
  5. Rationality of business operational forecasts: evidence from Malaysian distributive trade sector By Puah, Chin-Hong; Wong, Shirly Siew-Ling; Habibullah, Muzafar Shah
  6. Bayesian Model Averaging, Learning and Model Selection By Evans, George W.; Honkapohja, Seppo; Sargent, Thomas J; Williams, Noah
  7. Is customer satisfaction a relevant metric for financial analysts? By Paul-Valentin Ngobo; Jean-François Casta; Olivier Ramond
  8. Estimating Relative Risk Aversion, Risk-Neutral and Real-World Densities using Brazilian Real Currency Options By José Renato Haas Ornelas; José Santiago Fajardo Barbachan; Aquiles Rocha de Farias
  9. Aftershock prediction for high-frequency financial markets' dynamics By Fulvio Baldovin; Francesco Camana; Michele Caraglio; Attilio L. Stella; Marco Zamparo
  10. The information content of central bank interest rate projections: Evidence from New Zealand By Gunda-Alexandra Detmers; Dieter Nautz
  11. Stress testing German banks against a global cost-of-capital shock By Duellmann, Klaus; Kick, Thomas

  1. By: David F. Hendry; Grayham E. Mizon
    Abstract: Understanding the workings of whole economies is essential for sound policy advice - but not necessarily for accurate forecasts. Structural models play a major role at most central banks and many other governmental agencies, yet almost none forecast the financial crisis and ensuing recession. We focus on the problem of forecast failure that has become prominent during and after that crisis, and illustrate its sources and many surprising implications using a simple model. An application to ‘forecasting’ UK GDP over 2008(1)-2011(2) is consistent with our interpretation.
    Keywords: Structural models, Location shifts, Economic forecasting, Autometrics
    JEL: C52 C22
    Date: 2012
  2. By: Claudia Godbout (Bank of Canada, International Department, 234 Wellington Street, Ottawa, Ontario K1A 0G9, Canada.); Marco J. Lombardi (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.)
    Abstract: While the usefulness of factor models has been acknowledged over recent years, little attention has been devoted to the forecasting power of these models for the Japanese economy. In this paper, we aim at assessing the relative performance of factor models over different samples, including the recent financial crisis. To do so, we construct factor models to forecast Japanese GDP and its subcomponents, using 38 data series (including daily, monthly and quarterly variables) over the period 1991 to 2010. Overall, we find that factor models perform well at tracking GDP movements and anticipating turning points. For most of the components, we report that factor models yield lower forecasting errors than a simple AR process or an indicator model based on Purchasing Managers' Indicators (PMIs). In line with previous studies, we conclude that the largest improvements in terms of forecasting accuracy are found for more volatile periods, such as the recent financial crisis. However, unlike previous studies, we do not find evident links between the volatility of the components and the relative advantage of using factor models. Finally, we show that adding the PMI index as an independent explanatory variable improves the forecasting properties of the factor models. JEL Classification: C50, C53, E37, E47.
    Keywords: Japan, forecasting, nowcasting, factor models, mixed frequency.
    Date: 2012–03
  3. By: Sinha, Pankaj; Jayaraman, Prabha
    Abstract: The paper presents a comparative study of conventional beta adjustment techniques and suggests an improved Bayesian model for beta forecasting. The seminal papers of Blume (1971) and Levy (1971) suggested that for both single security and portfolio there was a tendency for relatively high and low beta coefficients to over predict and under predict, respectively, the corresponding betas for the subsequent time period. We utilize this proven fact to give a Bayesian adjustment technique under a bilinear loss function where the problem of overestimation and underestimation of future betas is rectified to an extent so as to give us improved beta forecasts. The accuracy and efficiency of our methodology with respect to existing procedures is shown by computing the mean square forecast error.
    Keywords: Bayesian Beta adjustment technique; bi-linear loss function; portfolio risk measure
    JEL: G12 G32 C1 C11
    Date: 2012–02–06
  4. By: Kimmo Ollikka; Piia Aatola; Markku Ollikainen
    Abstract: We study the informational efficiency of the European Emissions Trading Scheme, EU ETS market by simulating the trading in this emerging market. If the market is efficient, profitable trading should only exist locally in time. We adopt the Timmermann and Granger (2004) definition of efficiency and for the first time in the literature run a large set of econometric, technical analysis and combined models to forecast the emissions allowance price changes. These forecasts are then used as trading signals in the trading simulation. We find that the combined models outperform the other models in forecasting ability. Trading simulation based on models combining time series and technical analysis trading rules shows that there have been possibilities for profitable trading in the EU ETS market during the study period of 2008?2010. This suggests that the EU ETS market shows periods with no informational efficiency.
    Keywords: European Union emissions trading, informational efficiency, econometric analysis
    JEL: Q52 Q53
    Date: 2012–03–22
  5. By: Puah, Chin-Hong; Wong, Shirly Siew-Ling; Habibullah, Muzafar Shah
    Abstract: The underlying nature of forecast optimization makes the rational expectations hypothesis (REH) a framework that is theoretically consistent with the expectations formation produced by economic agents under well-defined assumptions of unbiased forecasts and efficient utilization of available information. Most of the recent literature on REH testing has favored a direct procedure based on survey data to validate the theoretical soundness of REH. However, the ability of survey materials to reflect the economic agent’s true expectations remains unconvincing, as previous empirical studies on survey-based expectations have offered mixed evidence of forecast rationality. The present study involved an attempt to evaluate the forecast rationality of survey materials from the Malaysian perspective, as empirical evidence from the view of a developing nation is clearly limited. An expectational series on gross revenue and capital expenditure, spanning 1978 through 2007, was subjected to tests of unbiasedness, non-serial correlation, and efficiency to observe whether the business operational forecasts contributed by the distributive trade sector in Malaysia can be accepted as rational forecasts of the actual realized values. We found that both operational variables are being irrationally constructed, suggesting that forecasters in the distributive trade sector are not rational when they formulate business expectations. Thus, business firms in the examined sector are encouraged to incorporate more relevant information into their business operational forecasts to facilitate more accurate and realistic business forecasting.
    Keywords: Rational Expectations Hypothesis; Rationality tests; Survey Data; Distributive Trade
    JEL: D84 L81 C12 C22 C83
    Date: 2012–03
  6. By: Evans, George W.; Honkapohja, Seppo; Sargent, Thomas J; Williams, Noah
    Abstract: Agents have two forecasting models, one consistent with the unique rational expectations equilibrium, another that assumes a time-varying parameter structure. When agents use Bayesian updating to choose between models in a self-referential system, we find that learning dynamics lead to selection of one of the two models. However, there are parameter regions for which the non-rational forecasting model is selected in the long-run. A key structural parameter governing outcomes measures the degree of expectations feedback in Muth's model of price determination.
    Keywords: grain of truth; rational expectations equilibrium; Time-varying perceptions
    JEL: D83 D84 E37
    Date: 2012–03
  7. By: Paul-Valentin Ngobo (LOG - Laboratoire Orléanais de Gestion - Université d'Orléans); Jean-François Casta (DRM - Dauphine Recherches en Management - CNRS : UMR7088 - Université Paris IX - Paris Dauphine); Olivier Ramond (DRM - Dauphine Recherches en Management - CNRS : UMR7088 - Université Paris IX - Paris Dauphine)
    Abstract: This study examines the effects of customer satisfaction on analysts' earnings forecast errors. Based on a sample of analysts following companies measured by the American Customer Satisfaction Index (ACSI), we find that customer satisfaction reduces earnings forecast errors. However, analysts respond to changes in customer satisfaction but not to the ACSI metric per se. Furthermore, the effects of customer satisfaction are asymmetric; for example, analysts are more willing to use good news (i.e. an increase in customer satisfaction information) than bad news (i.e. a decrease in satisfaction). Similarly, customer satisfaction reduces negative deviation more than positive deviation of the analysts' forecasts from actual earnings. Furthermore, the effects of customer satisfaction depend upon the base level of satisfaction that the firm has achieved. Finally, the effects of customer satisfaction on analysts' forecast errors differ across firms with volatile satisfaction scores and those with stable satisfaction scores. We discuss the implications of our results for marketers and participants in financial markets.
    Keywords: Customer satisfaction ; EPS forecast errors ; Value relevance ; ACSI ; GMM dynamic models ; American Customer Satisfaction Index : Financial Analysts
    Date: 2012–05–01
  8. By: José Renato Haas Ornelas; José Santiago Fajardo Barbachan; Aquiles Rocha de Farias
    Abstract: Building Risk-Neutral Densities (RND) from options data can provide market-implied expectations about the future behavior of a financial variable. This paper uses the Liu et all (2007) approach to estimate the option-implied risk-neutral densities from the Brazilian Real/US Dollar exchange rate distribution. We then compare the RND with actual exchange rates, on a monthly basis, in order to estimate the relative risk-aversion of investors and also obtain a real-world density for the exchange rate. We are the first to calculate relative risk-aversion and the option-implied real world Density for an emerging market currency. Our empirical application uses a sample of exchange-traded Brazilian Real currency options from 1999 to 2011. The RND is estimated using a Mixture of Two Log-Normals distribution and then the real-world density is obtained by means of the Liu et al. (2007) parametric risk-transformations. Our estimated value of the relative risk aversion parameter is around 2.7, which is in line with other articles that have estimated this parameter for the Brazilian Economy. Our out-of-sample evaluation results showed that the RND has some ability to forecast the Brazilian Real exchange rate. However, when we incorporate the risk aversion into RND in order to obtain a Real-world density, the outof- sample performance improves substantially. Therefore, we would suggest not using the “pure” RND, but rather taking into account risk aversion in order to forecast the Brazilian Real exchange rate.
    Date: 2012–03
  9. By: Fulvio Baldovin; Francesco Camana; Michele Caraglio; Attilio L. Stella; Marco Zamparo
    Abstract: The occurrence of aftershocks following a major financial crash manifests the critical dynamical response of financial markets. Aftershocks put additional stress on markets, with conceivable dramatic consequences. Such a phenomenon has been shown to be common to most financial assets, both at high and low frequency. Its present-day description relies on an empirical characterization proposed by Omori at the end of 1800 for seismic earthquakes. We point out the limited predictive power in this phenomenological approach and present a stochastic model, based on the scaling symmetry of financial assets, which is potentially capable to predict aftershocks occurrence, given the main shock magnitude. Comparisons with S&P high-frequency data confirm this predictive potential.
    Date: 2012–03
  10. By: Gunda-Alexandra Detmers; Dieter Nautz (Reserve Bank of New Zealand)
    Abstract: The Reserve Bank of New Zealand was the first central bank to publish interest rate projections as a tool for forward guidance of monetary policy. This paper provides new evidence on the information content of interest rate projections for market expectations about future short-term rates before and during the financial crisis. While the information content of interest rate projections decreases with the forecast horizon in both periods, we find that their impact on market expectations has declined significantly since the outbreak of the crisis.
    JEL: E52 E58
    Date: 2012–02
  11. By: Duellmann, Klaus; Kick, Thomas
    Abstract: This paper introduces a stress test of the corporate credit portfolios of 24 large German banks by a two-stage approach: First, a macro-econometric model is used to forecast the impact of a substantial increase of the user cost of business capital for firms worldwide on three particularly export-oriented industry sectors in Germany. Second, the impact of this economic multi-sector stress on banks' credit portfolios is captured by a state-of-theart CreditMetrics-type portfolio model with sector-dependant unobservable risk factors as drivers of the systematic risk. The German credit register provides us with access to highly granular risk information on loan volumes and banks' internal estimates of default probabilities which is key for an accurate assessment of the impact of the stress scenario. We find that the increase of the capital charge for the unexpected loss needs to be considered together with the increase in banks' expected losses in order to assess the change of banks' capital ratios. We also confirm that highly granular information on the level of borrowerspecific probabilities of default has a significant impact on the outcome of the stress test. --
    Keywords: Asset correlation,portfolio credit risk,macroeconomic stress tests
    JEL: G21 G33 C13 C15
    Date: 2012

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.