nep-for New Economics Papers
on Forecasting
Issue of 2017‒02‒19
five papers chosen by
Rob J Hyndman
Monash University

  1. Data Revisions and Real-time Probabilistic Forecasting of Macroeconomic Variables By Michael P Clements; Ana Beatriz Galvao
  2. Should forecasters use real-time data to evaluate leading indicator models for GDP prediction? German evidence By Heinisch, Katja; Scheufele, Rolf
  3. A regime-switching stochastic volatility model for forecasting electricity prices By Knapik, Oskar; Exterkate, Peter
  4. Variance stabilizing transformations for electricity spot price forecasting By Bartosz Uniejewski; Rafal Weron; Florian Ziel
  5. Coordinating expectations through central bank projections By Fatemeh Mokhtarzadeh; Luba Petersen

  1. By: Michael P Clements (Henley Business School); Ana Beatriz Galvao (Warwick Business School)
    Abstract: Macroeconomic data are subject to revision over time as later vintages are released, yet the usual way of generating real-time out-of-sample forecasts from models effectively makes no allowance for this form of data uncertainty. We analyze a simple method which has been used in the context of point forecasting, and does make an allowance for data uncertainty. This method is applied to density forecasting in the presence of time-varying heteroscedasticity, and is shown in principle to improve real-time density forecasts. We show that the magnitude of the expected improvements depends on the nature of the data revisions.
    Keywords: real-time forecasting, inflation and output growth predictive densities, real-time-vintages, time-varying heteroscedasticity.
    JEL: C53
    Date: 2017–01
  2. By: Heinisch, Katja; Scheufele, Rolf
    Abstract: In this paper we investigate whether differences exist among forecasts using real-time or latest-available data to predict gross domestic product (GDP). We employ mixed-frequency models and real-time data to reassess the role of survey data relative to industrial production and orders in Germany. Although we find evidence that forecast characteristics based on real-time and final data releases differ, we also observe minimal impacts on the relative forecasting performance of indicator models. However, when obtaining the optimal combination of soft and hard data, the use of final release data may understate the role of survey information.
    Keywords: mixed-frequency VAR,real-time data,nowcasting,forecasting
    JEL: C53 C55 E37
    Date: 2017
  3. By: Knapik, Oskar; Exterkate, Peter
    Abstract: In a recent review paper, Weron (2014) pinpoints several crucial challenges outstanding in the area of electricity price forecasting. This research attempts to address all of them by i) showing the importance of considering fundamental price drivers in modeling, ii) developing new techniques for probabilistic (i.e. interval or density) forecasting of electricity prices, iii) introducing an universal technique for model comparison. We propose new regime-switching stochastic volatility model with three regimes (negative jump, normal price, positive jump (spike)) where the transition matrix depends on explanatory variables. Bayesian inference is explored in order to obtain predictive densities. The main focus of the paper is on short-time density forecasting in Nord Pool intraday market. We show that the proposed model outperforms several benchmark models at this task.
    Keywords: Electricity prices, density forecasting, Markov switching, stochastic volatility, fundamental price drivers, ordered probit model, Bayesian inference, seasonality, Nord Pool power market, electricity prices forecasting, probabilistic forecasting
    Date: 2017–02
  4. By: Bartosz Uniejewski; Rafal Weron; Florian Ziel
    Abstract: Most electricity spot price series exhibit price spikes. These extreme observations may significantly impact the obtained model estimates and hence reduce efficiency of the employed predictive algorithms. For markets with only positive prices the logarithmic transform is the single most commonly used technique to reduce spike severity and consequently stabilize the variance. However, for datasets with very close to zero (like the Spanish) or negative (like the German) prices the log-transform is not feasible. What reasonable choices do we have then? To address this issue, we conduct a comprehensive forecasting study involving 12 datasets from diverse power markets and evaluate 16 variance stabilizing transformations. We find that the probability integral transform (PIT) combined with the standard Gaussian distribution yields the best approach, significantly better than many of the considered alternatives.
    Keywords: Electricity spot price; Forecasting; Variance stabilizing transformation; Probability integral transform; Price spike; Diebold-Mariano test
    JEL: C14 C22 C51 C53 Q47
    Date: 2017–02–14
  5. By: Fatemeh Mokhtarzadeh (University of Victoria); Luba Petersen (Simon Fraser University)
    Abstract: This paper explores how expectations are influenced by central bank projections within a learning-to-forecast laboratory macroeconomy. Subjects are incentivized to forecast output and inflation in a laboratory macroeconomy where their aggregated expectations directly influence macroeconomic dynamics. Using a between-subject design, we systematically vary whether the central bank communicates no information, ex-ante rational nominal interest rate projections, or rational or adaptive dual projections of output and inflation. Our experimental findings suggest that interest rate projections and adaptive dual projections can encourage backward-looking forecasting behavior. Expectations are best coordinated and stabilized by communicating rational output and inflation forecasts.
    Keywords: expectations, monetary policy, projections, communication, credibility, laboratory experiment, experimental macroeconomics
    JEL: C9 D84 E52 E58
    Date: 2017–02

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.