nep-for New Economics Papers
on Forecasting
Issue of 2006‒09‒23
eight papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting Using Predictive Likelihood Model Averaging By George Kapetanios; Vincent Labhard; Simon Price
  3. Forecasting Euro-Area Variables with German Pre-EMU Data By Ralf Brüggemann; Helmut Lütkepohl; Massimiliano Marcellino
  4. Forecasting using Bayesian and Information Theoretic Model Averaging: An Application to UK Inflation By George Kapetanios; Vincent Labhard; Simon Price
  5. Empirical Bayesian density forecasting in Iowa and shrinkage for the Monte Carlo era By Lewis, Kurt F.; Whiteman, Charles H.
  6. Customer order flow, information and liquidity on the Hungarian foreign exchange market By Áron Gereben; György Gyomai; Norbert Kiss M.
  7. Forecasting with panel data By Baltagi, Badi H.
  8. The Sale of Alcohol in Denmark By Cour, Lisbeth la; Milhøj, Anders

  1. By: George Kapetanios (Queen Mary, University of London); Vincent Labhard (Bank of England); Simon Price (Bank of England and City University)
    Abstract: Recently, there has been increasing interest in forecasting methods that utilise large datasets. We explore the possibility of forecasting with model averaging using the out-of-sample forecasting performance of various models in a frequentist setting, using the predictive likelihood. We apply our method to forecasting UK inflation and find that the new method performs well; in some respects it outperforms other averaging methods.
    Keywords: Forecasting, Inflation, Bayesian model averaging, Akaike criterion, Forecast combining
    JEL: C11 C15 C53
    Date: 2006–09
  2. By: John Galbraith; Greg Tkacz
    Abstract: For stationary transformations of variables, there exists a maximum horizon beyond which forecasts can provide no more information about the variable than is present in the unconditional mean. Meteorological forecasts, typically excepting only experimental or exploratory situations, are not reported beyond this horizon; by contrast, little generally-accepted information about such maximum horizons is available for economic variables. In this paper we estimate such content horizons for a variety of economic variables, and compare these with the maximum horizons which we observe reported in a large sample of empirical economic forecasting studies. We find that there are many instances of published studies which provide forecasts exceeding, often by substantial margins, our estimates of the content horizon for the particular variable and frequency. We suggest some simple reporting practices for forecasts that could potentially bring greater transparency to the process of making the interpreting economic forecasts.
    JEL: C53
    Date: 2006–09
  3. By: Ralf Brüggemann; Helmut Lütkepohl; Massimiliano Marcellino
    Abstract: It is investigated whether Euro-area variables can be forecast better based on synthetic time series for the pre-Euro period or by using just data from Germany for the pre-Euro period. Our forecast comparison is based on quarterly data for the period 1970Q1 - 2003Q4 for ten macroeconomic variables. The years 2000 - 2003 are used as forecasting period. A range of different univariate forecasting methods is applied. Some of them are based on linear autoregressive models and we also use some nonlinear or time-varying coefficient models. It turns out that most variables which have a similar level for Germany and the Euro-area such as prices can be better predicted based on German data while aggregated European data are preferable for forecasting variables which need considerable adjustments in their levels when joining German and EMU data. These results suggest that for variables which have a similar level for Germany and the Euro-area it may be reasonable to consider the German pre-EMU data for studying economic problems in the Euro-area.
    Keywords: Aggregation, forecasting, European monetary union, constructing EMU data
    JEL: C22 C53
    Date: 2006–09
  4. By: George Kapetanios (Queen Mary, University of London); Vincent Labhard (Bank of England); Simon Price (Bank of England)
    Abstract: In recent years there has been increasing interest in forecasting methods that utilise large datasets, driven partly by the recognition that policymaking institutions need to process large quantities of information. Factor analysis is one popular way of doing this. Forecast combination is another, and it is on this that we concentrate. Bayesian model averaging methods have been widely advocated in this area, but a neglected frequentist approach is to use information theoretic based weights. We consider the use of model averaging in forecasting UK inflation with a large dataset from this perspective. We find that an information theoretic model averaging scheme can be a powerful alternative both to the more widely used Bayesian model averaging scheme and to factor models.
    Keywords: Forecasting, Inflation, Bayesian model averaging, Akaike criteria, Forecast combining
    JEL: C11 C15 C53
    Date: 2006–09
  5. By: Lewis, Kurt F.; Whiteman, Charles H.
    Abstract: The track record of a sixteen-year history of density forecasts of state tax revenue in Iowa is studied, and potential improvements sought through a search for better performing “priors” similar to that conducted two decades ago for point forecasts by Doan, Litterman, and Sims (Econometric Reviews, 1984). Comparisons of the point- and density-forecasts produced under the flat prior are made to those produced by the traditional (mixed estimation) “Bayesian VAR” methods of Doan, Litterman, and Sims, as well as to fully Bayesian, “Minnesota Prior” forecasts. The actual record, and to a somewhat lesser extent, the record of the alternative procedures studied in pseudo-real-time forecasting experiments, share a characteristic: subsequently realized revenues are in the lower tails of the predicted distributions “too often”. An alternative empirically-based prior is found by working directly on the probability distribution for the VAR parameters, seeking a betterperforming entropically tilted prior that minimizes in-sample mean-squared-error subject to a Kullback-Leibler divergence constraint that the new prior not differ “too much” from the original. We also study the closely related topic of robust prediction appropriate for situations of ambiguity. Robust “priors” are competitive in out-of-sample forecasting; despite the freedom afforded the entropically tilted prior, it does not perform better than the simple alternatives.
    Date: 2006
  6. By: Áron Gereben (Magyar Nemzeti Bank); György Gyomai (Magyar Nemzeti Bank (at the time of writing)); Norbert Kiss M. (Magyar Nemzeti Bank)
    Abstract: Customer order flow – signed transaction volume between market makers and their customers – is a key concept in the microstructure approach to exchange rates. We attempt to explore what the data tells us about the role of customer order flow in the market for Hungarian forint, using the standard analytical framework of the FX microstructure literature. Our results confirm that customer order flow helps to explain exchange rate fluctuations, which suggests that customer order flow is a key source of information for the market makers. We also find that domestic and foreign customers play significantly different roles on the euro/Hungarian forint market: foreign players' order flow seems to provide the information that drives exchange rate fluctuations, whereas domestic customers are the source of market liquidity. We present evidence suggesting that current order flow from customers is able to provide a significantly better ‘forecast’ for the the exchange rate than the random walk benchmark in a simple Meese-Rogoff-type framework. However, we were unable to improve upon the random walk in a more realistic forecasting exercise. Finally, we highlight some features of our data that suggest that beyond microstructure, the traditional portfolio-balance channel of exchange rate determination is also in place.
    Keywords: customer order flow, microstructure, exchange rate.
    JEL: F31 G15
    Date: 2006
  7. By: Baltagi, Badi H.
    Abstract: This paper gives a brief survey of forecasting with panel data. Starting with a simple error component regression and surveying best linear unbiased prediction under various assumptions of the disturbance term. This includes various ARMA models as well as spatial autoregressive models. The paper also surveys how these forecasts have been used in panal data applications, running horse races between heterogeneous and homogeneous panel data models using out of sample forecasts.
    Keywords: Forecasting, BLUP, Panel Data, Spatial Dependence, Serial Correlation
    JEL: C33
    Date: 2006
  8. By: Cour, Lisbeth la (Department of Economics, Copenhagen Business School); Milhøj, Anders (Department of Economics, Copenhagen Business School)
    Abstract: In the following we will analyse the sale of alcohol in Denmark. Various figures related to this question are published by Statistics Denmark at different frequencies. Our main concern will be with quarterly data for the sale of beer, wine and spirits from the period 1990 – 2004. Our two hypotheses are: First we want to convince the reader that the total sale of alcohol in Denmark since 1980 has been fairly stable. By total sale we mean the total sale of 100% alcohol so the three categories – beer, wine and spirits are measured in litres of 100% alcohol equivalents. In order to convince the reader that the total sale of alcohol has been fairly constant we will present graphs and various indicators and tests of the degree of temporal dependence in this series. The overall impression from this analysis is that our first hypothesis seems to be supported – at least not contradicted – by the data. Next, we want to model the sale of beer and wine as shares of the total sale of alcohol. Even though the total sale can be considered fairly stable there have been divergent paths of evolvement for the sub-groups: the sale of beer has decreased over the period and the sale of wine has increased. The sale of spirits has been fairly stable. Modelling the system of the beer-share and the wine-share we want to split the total development into a part that can be ascribed to changes in the relative prices and a part that can be explained by changes in taste and drinking habits specified as a trend. By specifying a system conditionally on the prices of beer, wine and spirits and a trend we manage to estimate price sensitivity and taste sensitivity. A small forecasting exercise shows that the final model is fairly good at predicting changes in the shares due to price changes. Finally, the effects on the market shares of hypothetical changes in the taxation of alcohol are discussed.
    Keywords: Alcohol; Sale; drinking habits
    JEL: H00
    Date: 2005–09–14

This nep-for issue is ©2006 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.