nep-for New Economics Papers
on Forecasting
Issue of 2011‒10‒15
eleven papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting the Price of Oil By Ron Alquist; Lutz Kilian; Robert J. Vigfusson
  2. Forecast Evaluation in Call Centers: Combined Forecasts, Flexible Loss Functions and Economic Criteria By Andrea Bastianin; Marzio Galeotti; Matteo Manera
  3. Trend-cycle decomposition of output and euro area inflation forecasts: a real-time approach based on model combination By Pierre Guérin; Laurent Maurin; Matthias Mohr
  4. Evaluating the forecast quality of GDP components By Paulo Júlio; Pedro M. Esperança; João C. Fonseca
  5. Real-Time Forecasts of the Real Price of Oil By Christiane Baumeister; Lutz Kilian
  6. Do Experts incorporate Statistical Model Forecasts and should they? By Rianne Legerstee; Philip Hans Franses; Richard Paap
  7. Identification of Demand through Statistical Distribution Modeling for Improved Demand Forecasting By Murphy Choy; Michelle L. F. Cheong
  8. Forecasting the role of public expenditure in economic growth Using DEA-neural network approach By Amiri, Arshia; Ventelou, Bruno
  9. Cointegrated VARMA models and forecasting US interest rates By Christian Kascha; Carsten Trenkler
  10. CoVaR By Tobias Adrian; Markus K. Brunnermeier
  11. A Multi-Scenario Forecast of Urban Change: A Study on Urban Growth in the Algarve By Eric de Noronha Vaz; Peter Nijkamp; Marco Painho; Mario Gaetano

  1. By: Ron Alquist; Lutz Kilian; Robert J. Vigfusson
    Abstract: We address some of the key questions that arise in forecasting the price of crude oil. What do applied forecasters need to know about the choice of sample period and about the tradeoffs between alternative oil price series and model specifications? Are real or nominal oil prices predictable based on macroeconomic aggregates? Does this predictability translate into gains in out-of-sample forecast accuracy compared with conventional no-change forecasts? How useful are oil futures markets in forecasting the price of oil? How useful are survey forecasts? How does one evaluate the sensitivity of a baseline oil price forecast to alternative assumptions about future demand and supply conditions? How does one quantify risks associated with oil price forecasts? Can joint forecasts of the price of oil and of U.S. real GDP growth be improved upon by allowing for asymmetries?
    Keywords: Econometric and statistical methods; International topics
    JEL: C53 Q43
    Date: 2011
  2. By: Andrea Bastianin (University of Milan-Bicocca); Marzio Galeotti (University of Milan); Matteo Manera (University of Milan-Bicocca)
    Abstract: Accurate forecasts of incoming calls are crucial to optimal staffing decisions in call centers. This paper evaluates a wide range of models and forecast combination techniques by means of statistical and economic criteria. Relative to the previous literature, this paper is novel in several respects. In particular, the statistical evaluation of competing models is carried out by using a flexible loss function as input to pairwise and joint forecast diagnostic checks. Informative rankings across alternative single models and different groups of models are obtained. Moreover, models are evaluated from the perspective of a manager, who needs reliable forecasts to dimension the call center. Money metrics of forecasting performance are computed, which are based on the economic value of information and the certainty equivalent.
    Keywords: Combining forecasts, Decision making, Loss function, Seasonality, Telecommunications forecasting,
    Date: 2011–03–21
  3. By: Pierre Guérin (International Economic Analysis Department, Bank of Canada, 234 Wellington Street, Ottawa, Canada, K1A 0G9 and European University Institute); Laurent Maurin (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt, Germany.); Matthias Mohr (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt, Germany.)
    Abstract: The paper focuses on the estimation of the euro area output gap. We construct model-averaged measures of the output gap in order to cope with both model uncertainty and parameter instability that are inherent to trend-cycle decomposition models of GDP. We first estimate nine models of trend-cycle decomposition of euro area GDP, both univariate and multivariate, some of them allowing for changes in the slope of trend GDP and/or its error variance using Markov-switching specifications, or including a Phillips curve. We then pool the estimates using three weighting schemes. We compute both ex-post and real-time estimates to check the stability of the estimates to GDP revisions. We finally run a forecasting experiment to evaluate the predictive power of the output gap for inflation in the euro area. We find evidence of changes in trend growth around the recessions. We also find support for model averaging techniques in order to improve the reliability of the potential output estimates in real time. Our measures help forecasting inflation over most of our evaluation sample (2001-2010) but fail dramatically over the last recession. JEL Classification: C53, E32, E37.
    Keywords: Trend-cycle decomposition, Phillips curve, unobserved components model, Kalman Filter, Markov-switching, auxiliary information, model averaging, inflation forecast, real-time analysis.
    Date: 2011–10
  4. By: Paulo Júlio (Gabinete de Estratégia e Estudos, Portuguese Ministry of Economy and Employment, and NOVA School of Business and Economics); Pedro M. Esperança (Currently M.Sc. student at the University of Oxford. This article was written while the author was visiting at the Gabinete de Estratégia e Estudos, Portuguese Ministry of Economy and Employment); João C. Fonseca (Gabinete de Estratégia e Estudos, Portuguese Ministry of Economy and Employment)
    Abstract: We assess and compare the quality of forecasts issued for Portugal, at several time spans. Our analysis, covering the 2002-2010 period, focuses on real GDP growth and the corresponding expenditure components. We use a scaled statistic to compare the forecast accuracy of GDP components with different volatility levels, and explore the contributions of expenditure components to the GDP forecast error. Moreover, we propose two new statistics – termed Mean of Total Weighted Absolute Error and Mean of Total Weighted Squared Error – to evaluate the overall accuracy of components' predictions. The results suggest that GDP forecasts are generally optimistic at longer horizons (1-year ahead predictions), mainly due to overly optimistic forecasts in investment and exports. At shorter horizons (same-year predictions), GDP forecasts are more accurate, but this is achieved with relatively large errors in components' predictions, whose effects tend to cancel out.
    Keywords: Forecast evaluation, GDP expenditure components, Contributions to GDP growth, Mean of total weighted absolute error, Mean of total weighted squared error, Portugal
    Date: 2011–10
  5. By: Christiane Baumeister; Lutz Kilian
    Abstract: We construct a monthly real-time data set consisting of vintages for 1991.1-2010.12 that is suitable for generating forecasts of the real price of oil from a variety of models. We document that revisions of the data typically represent news, and we introduce backcasting and nowcasting techniques to fill gaps in the real-time data. We show that real-time forecasts of the real price of oil can be more accurate than the no-change forecast at horizons up to one year. In some cases real-time MSPE reductions may be as high as 25 percent one month ahead and 24 percent three months ahead. This result is in striking contrast to related results in the literature for asset prices. In particular, recursive vector autoregressive (VAR) forecasts based on global oil market variables tend to have lower MSPE at short horizons than forecasts based on oil futures prices, forecasts based on AR and ARMA models, and the no-change forecast. In addition, these VAR models have consistently higher directional accuracy. We demonstrate how with additional identifying assumptions such VAR models may be used not only to understand historical fluctuations in the real price of oil, but to construct conditional forecasts that reflect hypothetical scenarios about future demand and supply conditions in the market for crude oil. These tools are designed to allow forecasters to interpret their oil price forecast in light of economic models and to evaluate its sensitivity to alternative assumptions.
    Keywords: Econometric and statistical methods; International topics
    JEL: Q43 C53 E32
    Date: 2011
  6. By: Rianne Legerstee (Erasmus University Rotterdam); Philip Hans Franses (Erasmus University Rotterdam); Richard Paap (Erasmus University Rotterdam)
    Abstract: Experts can rely on statistical model forecasts when creating their own forecasts. Usually it is not known what experts actually do. In this paper we focus on three questions, which we try to answer given the availability of expert forecasts and model forecasts. First, is the expert forecast related to the model forecast and how? Second, how is this potential relation influenced by other factors? Third, how does this relation influence forecast accuracy? We propose a new and innovative two-level Hierarchical Bayes model to answer these questions. We apply our proposed methodology to a large data set of forecasts and realizations of SKU-level sales data from a pharmaceutical company. We find that expert forecasts can depend on model forecasts in a variety of ways. Average sales levels, sales volatility, and the forecast horizon influence this dependence. We also demonstrate that theoretical implications of expert behavior on forecast accuracy are reflected in the empirical data.
    Keywords: model forecasts; expert forecasts; forecast adjustment; Bayesian analysis; endogeneity
    JEL: C11 C53
    Date: 2011–10–04
  7. By: Murphy Choy; Michelle L. F. Cheong
    Abstract: Demand functions for goods are generally cyclical in nature with characteristics such as trend or stochasticity. Most existing demand forecasting techniques in literature are designed to manage and forecast this type of demand functions. However, if the demand function is lumpy in nature, then the general demand forecasting techniques may fail given the unusual characteristics of the function. Proper identification of the underlying demand function and using the most appropriate forecasting technique becomes critical. In this paper, we will attempt to explore the key characteristics of the different types of demand function and relate them to known statistical distributions. By fitting statistical distributions to actual past demand data, we are then able to identify the correct demand functions, so that the the most appropriate forecasting technique can be applied to obtain improved forecasting results. We applied the methodology to a real case study to show the reduction in forecasting errors obtained.
    Date: 2011–09
  8. By: Amiri, Arshia; Ventelou, Bruno
    Abstract: This paper integrates data envelopment analysis (DEA) and artificial neural networks (ANN) to forecast the role of public expenditure in economic growth in OCDE countries. The results show that this approach is a powerful and appropriate method to forecast this role. DEA method allows us to develop a neutral evaluation, unbiased a priori by any type of criteria, of the proportions in which the goal of productive spending is pursued, for any expenditure. Then we apply ANN to forecast economic growth by using input data taken at frontier. At the end of the DEA-ANN chain, prediction-power tests appear positive: best structures of multiple hidden layers indicate more ability to forecast according to best structures of single hidden layer but the difference between those is not much.
    Keywords: DEA method; Economic growth; Public expenditure; Artificial neural network; OCDE countries
    JEL: C53 G18 G38 H5
    Date: 2011–09–13
  9. By: Christian Kascha; Carsten Trenkler
    Abstract: We bring together some recent advances in the literature on vector autoregressive moving-average models creating a relatively simple specification and estimation strategy for the cointegrated case. We show that in the cointegrated case with fixed initial values there exists a so-called final moving representation which is usually simpler but not as parsimonious than the usual Echelon form. Furthermore, we proof that our specification strategy is consistent also in the case of cointegrated series. In order to show the potential usefulness of the method, we apply it to US interest rates and find that it generates forecasts superior to methods which do not allow for moving-average terms.
    Keywords: Cointegration, VARMA models, forecasting
    JEL: C32 C53 E43 E47
    Date: 2011–10
  10. By: Tobias Adrian; Markus K. Brunnermeier
    Abstract: We propose a measure for systemic risk: CoVaR, the value at risk (VaR) of the financial system conditional on institutions being under distress. We define an institution's contribution to systemic risk as the difference between CoVaR conditional on the institution being under distress and the CoVaR in the median state of the institution. From our estimates of CoVaR for the universe of publicly traded financial institutions, we quantify the extent to which characteristics such as leverage, size, and maturity mismatch predict systemic risk contribution. We also provide out of sample forecasts of a countercyclical, forward looking measure of systemic risk and show that the 2006Q4 value of this measure would have predicted more than half of realized covariances during the financial crisis.
    JEL: G21 G22
    Date: 2011–10
  11. By: Eric de Noronha Vaz (Universidade Nova de Lisboa); Peter Nijkamp (VU University Amsterdam); Marco Painho (Universidade NOVA de Lisboa); Mario Gaetano (Universidade NOVA de Lisboa)
    Abstract: The Algarve region in Portugal is often considered as one of the most appealing regions for tourism in the country. Its attractive location and moderate climate have since the mid-1960s brought increasing economic prosperity. As a result of the development of mass tourism, available land-use resources were widely exploited to create an integrated tourist industry. This region has shown an increasing loss of ecosystems resulting from the expansion of urban areas. This has also been accompanied by a significant abandonment of rural areas and hinterlands, leading to loss of agriculture and other rural activities. Clearly, urban growth needs considerable attention in the context of sustainable development, as often peri-urban areas with fragile ecosystems are becoming increasingly vulnerable. This paper aims to develop and apply key tools to quantify the changes of land use and how this affects the regional spatial scope by using multi-temporal inventorying an d accounting of land-use change matrices. Using Cellular Automata and a combined interpretation of CORINE Land Cover Data, it converges into a qualitative to quantitative interpretation of land use change by means of Multi-Criteria Evaluation. Finally, our analysis to identify the scenario with the best fit, based on the evolution of the actual 2006 land cover, enabled us to build a future urban growth model for 2020 which was quantitatively assessed. The outcome suggests a picture of continuing growth for the region of the Algarve within the framework of current policies and regressive spatial trends.
    Keywords: Urban growth; Algarve; CORINE Land Cover; Scenario modelling
    JEL: R11 R14 C50
    Date: 2011–10–04

This nep-for issue is ©2011 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.