nep-for New Economics Papers
on Forecasting
Issue of 2017‒03‒19
five papers chosen by
Rob J Hyndman
Monash University

  1. A comprehensive evaluation of macroeconomic forecasting methods By Andrea Carriero; Galvao, Ana Beatriz; Kapetanios, George
  2. Forecasting oil prices By Degiannakis, Stavros; Filis, George
  3. Statistical and Economic Evaluation of Time Series Models for Forecasting Arrivals at Call Centers By Bastianin, Andrea; Galeotti, Marzio; Manera, Matteo
  4. Data Revisions and DSGE Models By Galvao, Ana Beatriz
  5. What univariate models tell us about multivariate macroeconomic models By Mitchell, James; Robertson, Donald; Wright, Stephen

  1. By: Andrea Carriero (Queen Mary University of London); Galvao, Ana Beatriz (University of Warwick); Kapetanios, George (Kings College London)
    Abstract: This paper contributes to the academic literature and the practice of macroeconomic forecasting. Our evaluation compares the performance of four classes of state-of-art forecasting models : Factor-Augmented Distributed Lag (FADL) Models, Mixed Data Sampling (MIDAS) Models, Bayesian Vector Autoregressive (BVAR) Models and a medium-sized Dynamic Stochastic General Equilibrium Model (DSGE). We look at these models to predict output growth and ination with datasets from the US, UK, Euro Area, Germany, France, Italy and Japan. We evaluate the accuracy of point and density forecasts, and compare models with a large set of predictors with models that employ a medium-sized dataset. Our empirical results shed light on how the predictive ability of economic indicators for output growth and ination changes with horizon, on the impact of dataset size on the calibration of density forecasts, and how the choice of the multivariate forecasting model depends on the forecasting horizon.
    Keywords: factor models ; BVAR models ; MIDAS models ; DSGE models ; density forecasts JEL Classification Numbers: C53
    Date: 2016
  2. By: Degiannakis, Stavros; Filis, George
    Abstract: Accurate and economically useful oil price forecasts have gained significant importance over the last decade. The majority of the studies use information from the oil market fundamentals to generate oil price forecasts. Nevertheless, the extant literature has convincingly shown that oil prices are nowadays interconnected with the financial and commodities markets. Despite this, there is scarce evidence as to whether information from these markets could improve the forecasting accuracy of oil prices. Even more, there is limited knowledge whether high frequency data, given their rich information, could improve monthly oil prices. In this study we fill this void, employing a Mixed Data-Sampling (MIDAS) method using both oil market fundamentals and high frequency data from 15 financial and commodities assets. Our findings show that either the daily realized volatilities or daily returns of these assets significantly improve oil price forecasts relatively to the no-change forecast, as well as, relatively to the well-established models of the literature. These results hold true even when we consider tranquil and turbulent oil market conditions.
    Keywords: Oil price forecasting, Brent crude oil, intra-day data, MIDAS.
    JEL: C53 G14 G15 Q43 Q47
    Date: 2017–03–14
  3. By: Bastianin, Andrea; Galeotti, Marzio; Manera, Matteo
    Abstract: Call centers' managers are interested in obtaining accurate forecasts of call arrivals because these are a key input in staffing and scheduling decisions. Therefore their ability to achieve an optimal balance between service quality and operating costs ultimately hinges on forecast accuracy. We present a strategy to model selection in call centers which is based on three pillars: (i) a flexible loss function; (ii) statistical evaluation of forecast accuracy; (iii) economic evaluation of forecast performance using money metrics. We implement fourteen time series models and seven forecast combination schemes on three series of call arrivals. We show that second moment modeling is important when forecasting call arrivals. From the point of view of a call center manager, our results indicate that outsourcing the development of a forecasting model is worth its cost, since the simple Seasonal Random Walk model is always outperformed by other, relatively more sophisticated, specifications.
    Keywords: ARIMA, Call Center Arrivals, Loss Function, Seasonality, Telecommunications Forecasting, Research Methods/ Statistical Methods, C22, C25, C53, D81, M15,
    Date: 2017–03–03
  4. By: Galvao, Ana Beatriz (Warwick Business School, University of Warwick)
    Abstract: The typical estimation of DSGE models requires data on a set of macroeconomic aggregates, such as output, consumption and investment, which are subject to data revisions. The conventional approach employs the time series that is currently available for these aggregates for estimation, implying that the last observations are still subject to many rounds of revisions. This paper proposes a release-based approach that uses revised data of all observations to estimate DSGE models, but the model is still helpful for real-time forecasting. This new approach accounts for data uncertainty when predicting future values of macroeconomic variables subject to revisions, thus providing policy-makers and professional forecasters with both backcasts and forecasts. Application of this new approach to a medium-sized DSGE model improves the accuracy of density forecasts, particularly the coverage of predictive intervals, of US real macrovariables. The application also shows that the estimated relative importance of business cycle sources varies with data maturity.
    Keywords: data revisions ; medium-sized DSGE models ; forecasting ; variance decomposition JEL Classification Numbers: C53
    Date: 2016
  5. By: Mitchell, James (Warwick Business School, University of Warwick); Robertson, Donald (Faculty of Economics, University of Cambridge); Wright, Stephen (Department of Economics, Maths & Statistics Birkbeck College, University of London)
    Abstract: A longstanding puzzle in macroeconomic forecasting has been that a wide variety of multivariate models have struggled to out-predict univariate representations. We seek an explanation for this puzzle in terms of population properties. We show that if we just know the univariate properties of a time-series, yt, this can tell us a lot about the dimensions and the predictive power of the true (but unobservable) multivariate macroeconomic model that generated yt. We illustrate using data on U.S. inflation. We find that, especially in recent years, the univariate properties of inflation dictate that even the true multivariate model for inflation would struggle to out-predict a univariate model. Furthermore, predictions of changes in ination from the true model would either need to be IID or have persistence properties quite unlike those of most current macroeconomic models.
    Keywords: Forecasting ; Macroeconomic Models ; Autoregressive Moving Average Representations ; Predictive Regressions ; Nonfundamental Representations ; Inflation Forecasts JEL Classification Numbers: C22 ; C32 ; C53 ; E37
    Date: 2016

This nep-for issue is ©2017 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.