nep-for New Economics Papers
on Forecasting
Issue of 2010‒11‒27
eight papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting Compositional Time Series with Exponential Smoothing Methods By Anne B. Koehler; Ralph D. Snyder; J. Keith Ord; Adrian Beaumont
  2. Nonparametric modeling and forecasting electricity demand: an empirical study By Han Lin Shang
  3. How useful is the carry-over effect for short-term economic forecasting? By Tödter, Karl-Heinz
  4. Do FOMC Members Herd? By Jan-Christoph Rülke; Peter Tillmann
  5. Should macroeconomic forecasters use daily financial data and how? By Elena Andreou; Eric Ghysels; Andros Kourtellos
  6. Forecasting Short-Run Inflation Volatility using Futures Prices: An Empirical Analysis from a Value at Risk Perspective By Guillermo Benavides
  7. Does the macroeconomy predict U.K. asset returns in a nonlinear fashion? comprehensive out-of-sample evidence By Massimo Guidolin; Stuart Hyde; David McMillan; Sadayuki Ono
  8. A Forecasting Metric for Evaluating DSGE Models for Policy Analysis By Gupta, Abhishek

  1. By: Anne B. Koehler; Ralph D. Snyder; J. Keith Ord; Adrian Beaumont
    Abstract: Compositional time series are formed from measurements of proportions that sum to one in each period of time. We might be interested in forecasting the proportion of home loans that have adjustable rates, the proportion of nonagricultural jobs in manufacturing, the proportion of a rock's geochemical composition that is a specific oxide, or the proportion of an election betting market choosing a particular candidate. A problem may involve many related time series of proportions. There could be several categories of nonagricultural jobs or several oxides in the geochemical composition of a rock that are of interest. In this paper we provide a statistical framework for forecasting these special kinds of time series. We build on the innovations state space framework underpinning the widely used methods of exponential smoothing. We couple this with a generalized logistic transformation to convert the measurements from the unit interval to the entire real line. The approach is illustrated with two applications: the proportion of new home loans in the U.S. that have adjustable rates; and four probabilities for specified candidates winning the 2008 democratic presidential nomination.
    Keywords: compositional time series, innovations state space models, exponential smoothing, forecasting proportions
    JEL: C22
    Date: 2010–11
  2. By: Han Lin Shang
    Abstract: This paper uses half-hourly electricity demand data in South Australia as an empirical study of nonparametric modeling and forecasting methods for prediction from half-hour ahead to one year ahead. A notable feature of the univariate time series of electricity demand is the presence of both intraweek and intraday seasonalities. An intraday seasonal cycle is apparent from the similarity of the demand from one day to the next, and an intraweek seasonal cycle is evident from comparing the demand on the corresponding day of adjacent weeks. There is a strong appeal in using forecasting methods that are able to capture both seasonalities. In this paper, the forecasting methods slice a seasonal univariate time series into a time series of curves. The forecasting methods reduce the dimensionality by applying functional principal component analysis to the observed data, and then utilize an univariate time series forecasting method and functional principal component regression techniques. When data points in the most recent curve are sequentially observed, updating methods can improve the point and interval forecast accuracy. We also revisit a nonparametric approach to construct prediction intervals of updated forecasts, and evaluate the interval forecast accuracy.
    Keywords: Functional principal component analysis; functional time series; multivariate time series, ordinary least squares, penalized least squares; ridge regression; seasonal time series
    JEL: C88 C63 C14 C22
    Date: 2010–10–18
  3. By: Tödter, Karl-Heinz
    Abstract: The carry-over effect is the advance contribution of the old year to growth in the new year. Among practitioners the informative content of the carry-over effect for short-term forecasting is undisputed and is used routinely in economic forecasting. In this paper, the carry-over effect is analysed 'statistically' and it is shown how it reduces the uncertainty of short-term economic forecasts. This is followed by an empirical analysis of the carry-over effect using simple forecast models as well as Bundesbank and Consensus projections. --
    Keywords: forecast uncertainty,growth rates,carry-over effect,variance contribution,Chebyshev density
    JEL: C53 E37 C16
    Date: 2010
  4. By: Jan-Christoph Rülke (WHU - Otto Beisheim School of Management,WHU - Otto Beisheim School of Management); Peter Tillmann (Justus-Liebig-University Giessen)
    Abstract: Twice a year FOMC members submit forecasts for growth, unemplyoment and in ation to be published in the Humphrey-Hawkins Report to Congress. In this paper we use individual FOMC forecasts to assess whether these forecasts exhibit herding behavior, a pattern often found in private sector forecasts. While growth and unemployment forecast do not show herding behavior, the in ation forecasts show strong evidence of anti-herding, i.e. FOMC members intentionally scatter their forecasts around the consensus. Interestingly, anti-herding is more important for nonvoting members than for voters.
    Keywords: Central Federal Open Market Committee, monetary policy, forecasting, herding
    JEL: E43 E52 E27
    Date: 2010
  5. By: Elena Andreou; Eric Ghysels; Andros Kourtellos
    Abstract: We introduce easy to implement regression-based methods for predicting quarterly real economic activity that use daily financial data and rely on forecast combinations of MIDAS regressions. Our analysis is designed to elucidate the value of daily information and provide real-time forecast updates of the current (nowcasting) and future quarters. Our findings show that while on average the predictive ability of all models worsens substantially following the financial crisis, the models we propose suffer relatively less losses than the traditional ones. Moreover, these predictive gains are primarily driven by the classes of government securities, equities, and especially corporate risk.
    Keywords: MIDAS, macro forecasting, leads, daily financial information, daily factors.
    Date: 2010–11
  6. By: Guillermo Benavides
    Abstract: In this research paper ARCH-type models are applied in order to estimate the Value-at-Risk (VaR)of an inflation-index futures portfolio for several time-horizons. The empirical analysis is carried out for Mexican inflation-indexed futures traded at the Mexican Derivatives Exchange (MEXDER). To analyze the VaR with time horizons of more than one trading day bootstrapping simulations were applied. The results show that these models are relatively accurate for time horizons of one trading day. However, the volatility persistence of ARCH-type models is reflected with relatively high VaR estimates for longer time horizons. These results have implications for short-term inflation forecasts. By estimating confidence intervals in the VaR, it is possible to have certain confidence about the future range of inflation (or extreme inflation values) for a specified time horizon.
    Keywords: Bootstrapping, inflation, inflation-indexed futures, Mexico, value at risk, volatility persistence.
    JEL: C15 C22 C53 E31 E37
    Date: 2010–10
  7. By: Massimo Guidolin; Stuart Hyde; David McMillan; Sadayuki Ono
    Abstract: We perform a comprehensive examination of the recursive, comparative predictive performance of a number of linear and non-linear models for UK stock and bond returns. We estimate Markov switching, threshold autoregressive (TAR), and smooth transition autoregressive (STR) regime switching models, and a range of linear specifications in addition to univariate models in which conditional heteroskedasticity is captured by GARCH type specifications and in which predicted volatilities appear in the conditional mean. The results demonstrate that U.K. asset returns require non-linear dynamics be modeled. In particular, the evidence in favor of adopting a Markov switching framework is strong. Our results appear robust to the choice of sample period, changes in the adopted loss function and to the methodology employed to test the null hypothesis of equal predictive accuracy across competing models.>
    Keywords: Forecasting ; Econometric models ; Rate of return ; Great Britain
    Date: 2010
  8. By: Gupta, Abhishek
    Abstract: This paper evaluates the strengths and weaknesses of dynamic stochastic general equilibrium (DSGE) models from the standpoint of their usefulness in doing monetary policy analysis. The paper isolates features most relevant for monetary policymaking and uses the diagnostic tools of posterior predictive analysis to evaluate these features. The paper provides a diagnosis of the observed flaws in the model with regards to these features that helps in identifying the structural flaws in the model. The paper finds that model misspecification causes certain pairs of structural shocks in the model to be correlated in order to fit the observed data.
    Keywords: Posterior predictive analysis; DSGE; Monetary Policy; Forecast Errors; Model Evaluation.
    JEL: E58 C52 E1 C11
    Date: 2010–10–30

This nep-for issue is ©2010 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.