New forecasting papers 2008-08-18

In this issue we have: Post-Construction Evaluation of Traffic Forecast Accuracy ; Bayesian Demographic Modeling and Forecasting: An Application to U.S. Mortality ; Forecasting Elections from Voters’ Perceptions of Candidates’ Positions on Issues and Policies and more.


  • Post-Construction Evaluation of Traffic Forecast Accuracy
    Date: 2008
    By: Pavithra Parthasarathi
    David Levinson (Nexus (Networks, Economics, and Urban Systems) Research Group, Department of Civil Engineering, University of Minnesota)
    This research evaluates the accuracy of demand forecasts using a sample of recently-completed projects in Minnesota and identiÞes the factors inßuencing the inaccuracy in forecasts. The forecast traffic data for this study is drawn from Environmental Impact Statements(EIS), Transportation Analysis Reports (TAR) and other forecast reports produced by the Minnesota Department of Transportation (Mn/DOT) with a horizon forecast year of 2010 or earlier. The actual traffic data is compiled from the database of traffic counts maintained by the Office of Traffic Forecasting and Analysis section at Mn/DOT. Based on recent research on forecast accuracy, the (in)accuracy of traffic forecasts is estimated as a ratio of the forecast traffic to the actual traffic. The estimation of forecast (in)accuracy also involves a comparison of the socioeconomic and demographic assumptions, the assumed networks to the actual in-place net! works and other travel behavior assumptions that went into generating the traffic forecasts against actual conditions. The analysis indicates a general trend of underestimation in roadway traffic forecasts with factors such as highway type, functional classiÞcation, direction playing an inßuencing role. Roadways with higher volumes and higher functional classiÞcations such as freeways are subject to underestimation compared to lower volume roadways/functional classiÞcations. The comparison of demographic forecasts shows a trend of overestimation while the comparison of travel behavior characteristics indicates a lack of incorporation of fundamental shifts and societal changes.
    Keywords: Minnesota, Minneapolis, Travel Demand Model, Transportation Planning, Forecasting
    JEL: R41 R48 D63

  • Bayesian Demographic Modeling and Forecasting: An Application to U.S. Mortality
    Date: 2008-07
    By: Wolfgang Reichmuth
    Samad Sarferaz
    We present a new way to model age-specific demographic variables with the example of age-specific mortality in the U.S., building on the Lee-Carter approach and extending it in several dimensions. We incorporate covariates and model their dynamics jointly with the latent variables underlying mortality of all age classes. In contrast to previous models, a similar development of adjacent age groups is assured allowing for consistent forecasts. We develop an appropriate Markov Chain Monte Carlo algorithm to estimate the parameters and the latent variables in an efficient one-step procedure. Via the Bayesian approach we are able to asses uncertainty intuitively by constructing error bands for the forecasts. We observe that in particular parameter uncertainty is important for long-run forecasts. This implies that hitherto existing forecasting methods, which ignore certain sources of uncertainty, may yield misleadingly ! sure predictions. To test the forecast ability of our model we perform in-sample and out-of-sample forecasts up to 2050, revealing that covariates can help to improve the forecasts for particular age classes. A structural analysis of the relationship between age-specific mortality and covariates is conducted in a companion paper.
    Keywords: Demography, Age-specific, Mortality, Lee-Carter, Stochastic, Bayesian, State Space Models, Forecasts
    JEL: C11 C32 C53 I10 J11

  • Forecasting Elections from Voters' Perceptions of Candidates' Positions on Issues and Policies
    Date: 2008-08-04
    By: Graefe, Andreas
    Armstrong, J. Scott
    Ideally, presidential elections should be decided based on how the candidates would handle issues facing the country. If so, knowledge about the voters' perception of the candidates should help to forecast election outcomes. We make two forecasts of the winner of the popular vote in the U.S. Presidential Election. One is based on voters' perceptions of how the candidates would deal with issues (problems facing the country) if elected. We show that this approach would have correctly picked the winner for the three elections from 1996 to 2004. The other is based on voters' preference for policies and their perceptions of which policies the candidates are likely to pursue. Both approaches lead to a forecast that Democrat candidate Barack Obama will win the popular vote.
    Keywords: forecasting methods; regression models; index method; experience tables; accuracy
    JEL: C5
      Date: 2008-07
      By: John Galbraith
      Simon Van Norden
      A probabilistic forecast is the estimated probability with which a future event will satisfy a specified criterion. One interesting feature of such forecasts is their calibration, or the match between predicted probabilities and actual outcome probabilities. Calibration has been evaluated in the past by grouping probability forecasts into discrete categories. Here we show that we can do so without discrete groupings; the kernel estimators that we use produce efficiency gains and smooth estimated curves relating predicted and actual probabilities. We use such estimates to evaluate the empirical evidence on calibration error in a number of economic applications including recession and inflation prediction, using both forecasts made and stored in real time and pseudoforecasts made using the data vintage available at the forecast date. We evaluate outcomes using both first-release outcome measures as well as later, th! oroughly-revised data. We find strong evidence of incorrect calibration in professional forecasts of recessions and inflation. We also present evidence of asymmetries in the performance of inflation forecasts based on real-time output gaps.
      JEL: C73 D6 D9 O1 Q20
    2. Practical Volatility Modeling for Financial Market Risk Management
      Date: 2008-05-15
      By: Shamiri, Ahmed
      Shaari, Abu Hassan
      Isa, Zaidi
      Being able to choose most suitable volatility model and distribution specification is a more demanding task. This paper introduce an analyzing procedure using the Kullback-Leibler information criteria (KLIC) as a statistical tool to evaluate and compare the predictive abilities of possibly misspecified density forecast models. The main advantage of this statistical tool is that we use the censored likelihood functions to compute the tail minimum of the KLIC, to compare the performance of a density forecast models in the tails. We include an illustrative simulation and an empirical application to compare a set of distributions, including symmetric/asymmetric distribution, and a family of GARCH volatility models. We highlight the use of our approach to a daily index, the Kuala Lumpur Composite index (KLCI). Our results shows that the choice of the conditional distribution appear to be a more dominant factor in deter! mining the adequacy of density forecasts than the choice of volatility model. Furthermore, the results support the Skewed for KLCI return distribution.
      Keywords: Density forecast; Conditional distribution; Forecast accuracy; KLIC; GARCH models
      JEL: D53 C32 C16 C52
    3. Forecasting Using Functional Coefficients Autoregressive Models
      Date: 2008-06
      By: Giancarlo Bruno (ISAE – Institute for Studies and Economic Analyses)
      The use of linear parametric models for forecasting economic time series is widespread among practitioners, in spite of the fact that there is a large evidence of the presence of non-linearities in many of such time series. However, the empirical results stemming from the use of non-linear models are not always as good as expected. This has been sometimes associated to the difficulty in correctly specifying a non-linear parametric model. I this paper I cope with this issue by using a more general non-parametric approach, which can be used both as a preliminary tool for aiding in specifying a suitable parametric model and as an autonomous modelling strategy. The results are promising, in that the non-parametric approach achieve a good forecasting record for a considerable number of series.
      Keywords: Non-linear Time-Series Models, Non-Parametric Models.
      JEL: C52 C53
    4. The Information Content of Money in Forecasting Euro Area Inflation
      Date: 2008-07-09
      By: Helge Berger
      Emil Stavrev
      This paper contributes to the debate on the role of money in monetary policy by analyzing the information content of money in forecasting euro-area inflation. We compare the predictive performance within and among various classes of structural and empirical models in a consistent framework using Bayesian and other estimation techniques. We find that money contains relevant information for inflation in some model classes. Money-based New Keynesian DSGE models and VARs incorporating money perform better than their cashless counterparts. But there are also indications that the contribution of money has its limits. The marginal contribution of money to forecasting accuracy is often small, money adds little to dynamic factor models, and it worsens forecasting accuracy of partial equilibrium models. Finally, non-monetary models dominate monetary models in an all-out horserace.
      Keywords: Working Paper , Euro Area , Money , Inflation , Forecasting models , Monetary policy , Economic models ,
    5. Multivariate Fractionally Integrated APARCH Modeling of Stock Market Volatility: A multi-country study
      Date: 2008-07
      By: Christian Conrad (University of Heidelberg, Department of Economics)
      Menelaos Karanasos (Brunel University, Dept. of Economics and Finance)
      Ning Zeng (Brunel University, Dept. of Economics and Finance)
      Tse (1998) proposes a model which combines the fractionally integrated GARCH formulation of Baillie, Bollerslev and Mikkelsen (1996) with the asymmetric power ARCH speci¯cation of Ding, Granger and Engle (1993). This paper analyzes the applicability of a multivariate constant conditional correlation version of the model to national stock market returns for eight countries. We ¯nd this multivariate speci¯cation to be generally applicable once power, leverage and long-memory e®ects are taken into consideration. In addition, we ¯nd that both the optimal fractional di®erencing parameter and power transformation are remarkably similar across countries. Out-of-sample evidence for the superior forecasting ability of the multivariate FIAPARCH framework is provided in terms of forecast error statistics and tests for equal forecast accuracy of the various models.
      Keywords: Asymmetric Power ARCH, Fractional integration, Stock returns, Volatility forecast evaluation
      JEL: C13 C22 C52
    6. Forecasting inflation and tracking monetary policy in the euro area – does national information help?
      Date: 2008-06
      By: Riccardo Cristadoro (Banca d’Italia, Research Department, via Nazionale 91, I – 00184 Rome, Italy.)
      Fabrizio Venditti (Banca d’Italia, Research Department, via Nazionale 91, I – 00184 Rome, Italy.)
      Giuseppe Saporito (Banca d’Italia, Research Department, via Nazionale 91, I – 00184 Rome, Italy.)
      The ECB objective is set in terms of year on year growth rate of the Euro area HICP. Nonetheless, a good deal of attention is given to national data by market analysts when they try to anticipate monetary policy moves. In this paper we use the Generalized Dynamic Factor model to develop a set of core inflation indicators that, combining national data with area wide information, allow us to answer two related questions. The first is whether country specific data actually bear any relevance for the future path of area wide price growth, over and above that already contained in area wide data. The second is whether in order to track ECB monetary policy decisions it is useful to take into account national information and not only area wide statistics. In both cases our findings point to the conclusion that, once area wide information is properly taken into account, there is little to be gained from considering nationa! l idiosyncratic developments. JEL Classification: C25, E37, E52.
      Keywords: Forecasting, dynamic factor model, inflation, Taylor rule, monetary policy.
    7. Inflation Targeting and Communication: Should the Public Read Inflation Reports or Tea Leaves?
      Date: 2007-12
      By: Ales Bulir
      Katerina Smidkova
      Viktor Kotlan
      David Navratil
      Inflation-targeting central banks have a respectable track record at explaining their policy actions and corresponding inflation outturns. Using a simple forward-looking policy rule and an assessment of inflation reports, we provide a new methodology for the empirical evaluation of consistency in central bank communication. We find that the three communication tools—inflation targets, inflation forecasts, and verbal assessments of inflation factors contained in quarterly inflation reports—provided a consistent message in five out of six observations in our 2000–05 sample of Chile, the Czech Republic, Hungary, Poland, Thailand, and Sweden.
      Keywords: Emerging markets, forecasting, inflation targeting, monetary policy, transparency.
      JEL: E31 E43 E47 E58
    8. Predicting global stock returns
      Date: 2008
      By: Erik Hjalmarsson
      I test for stock return predictability in the largest and most comprehensive data set analyzed so far, using four common forecasting variables: the dividend- and earnings-price ratios, the short interest rate, and the term spread. The data contain over 20,000 monthly observations from 40 international markets, including 24 developed and 16 emerging economies. In addition, I develop new methods for predictive regressions with panel data. Inference based on the standard fixed effects estimator is shown to suffer from severe size distortions in the typical stock return regression, and an alternative robust estimator is proposed. The empirical results indicate that the short interest rate and the term spread are fairly robust predictors of stock returns in developed markets. In contrast, no strong or consistent evidence of predictability is found when considering


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