nep-for New Economics Papers
on Forecasting
Issue of 2020‒02‒03
ten papers chosen by
Rob J Hyndman
Monash University

  1. From Fixed-Event to Fixed-Horizon Density Forecasts: Obtaining Measures of Multi-Horizon Uncertainty from Survey Density Forecasts By Gegerly Ganics; Barbara Rossi; Tatevik Sekhposyan
  2. The predictive power of equilibrium exchange rate models By Mijakovic, Andrej; Rubaszek, Michał; Zorzi, Michele Ca’; Cap, Adam
  3. Forecasting with a Panel Tobit Model By Laura Liu; Hyungsik Roger Moon; Frank Schorfheide
  4. Forecasting industrial production in Germany: The predictive power of leading indicators By Schlösser, Alexander
  5. "Economic determinants of employment sentiment: A socio-demographic analysis for the euro area" By Oscar Claveria; Ivana Lolic; Enric Monte; Petar Soric
  6. Portfolio optimization based on forecasting models using vine copulas: An empirical assessment for the financial crisis By Maziar Sahamkhadam; Andreas Stephan
  7. Oil price uncertainty as a predictor of stock market volatility By Vlastakis, Nikolaos; Triantafyllou, Athanasios; Kellard, Neil
  8. On the Evaluation of Hierarchical Forecasts By George Athanasopoulos; Nikolaos Kourentzes
  9. A multi-country dynamic factor model with stochastic volatility for euro area business cycle analysis By Florian Huber; Michael Pfarrhofer; Philipp Piribauer
  10. Probability Assessments of an Ice-Free Arctic: Comparing Statistical and Climate Model Projections By Francis X. Diebold; Glenn D. Rudebusch

  1. By: Gegerly Ganics; Barbara Rossi; Tatevik Sekhposyan
    Abstract: Surveys of professional forecasters produce precise and timely point forecasts for key macroeconomic variables. However, the accompanying density forecasts are not as widely utilized, and there is no consensus about their quality. This is partly because such surveys are often conducted for “fixed events”. For example, in each quarter panelists are asked to forecast output growth and inflation for the current calendar year and the next, implying that the forecast horizon changes with each survey round. The fixed-event nature limits the usefulness of survey density predictions for policymakers and market participants, who often wish to characterize uncertainty a fixed number of periods ahead (“fixed-horizon”). Is it possible to obtain fixed-horizon density forecasts using the available fixed-event ones? We propose a density combination approach that weights fixed-event density forecasts according to a uniformity of the probability integral transform criterion, aiming at obtaining a correctly calibrated fixed-horizon density forecast. Using data from the US Survey of Professional Forecasters, we show that our combination method produces competitive density forecasts relative to widely used alternatives based on historical forecast errors or Bayesian VARs. Thus, our proposed fixed-horizon predictive densities are a new and useful tool for researchers and policy makers.
    Keywords: survey of professional forecasters, density forecasts, forecast combination, predictive density, probability integral transform, uncertainty, real-time
    JEL: C13 C32 C53
    Date: 2020–01
  2. By: Mijakovic, Andrej; Rubaszek, Michał; Zorzi, Michele Ca’; Cap, Adam
    Abstract: In this paper we evaluate the predictive power of the three most popular equilibrium exchange rate concepts: Purchasing Power Parity (PPP), Behavioral Equilibrium Exchange Rate (BEER) and the Macroeconomic Balance (MB) approach. We show that there is a clear trade-off between storytelling and forecast accuracy. The PPP model offers little economic insights, but has good predictive power. The BEER framework, which links exchange rates to fundamentals, does not deliver forecasts of better quality than PPP. The MB approach has the most appealing economic interpretation, but performs poorly in forecasting terms. Sensitivity analysis confirms that changing the composition of fundamentals in the BEER model or modifying key underlying assumptions in the MB model does not generally enhance their predictive power. JEL Classification: C33, F31, F37, F41
    Keywords: equilibrium exchange rate models, forecasting, mean reversion, panel data
    Date: 2020–01
  3. By: Laura Liu; Hyungsik Roger Moon; Frank Schorfheide
    Abstract: We use a dynamic panel Tobit model with heteroskedasticity to generate point, set, and density forecasts for a large cross-section of short time series of censored observations. Our fully Bayesian approach allows us to flexibly estimate the cross-sectional distribution of heterogeneous coefficients and then implicitly use this distribution as prior to construct Bayes forecasts for the individual time series. We construct set forecasts that explicitly target the average coverage probability for the cross-section. We present a novel application in which we forecast bank-level charge-off rates for credit card and residential real estate loans, comparing various versions of the panel Tobit model.
    JEL: C11 C14 C23 C53 G21
    Date: 2019–12
  4. By: Schlösser, Alexander
    Abstract: We investigate the predictive power of several leading indicators in order to forecast industrial production in Germany. In addition, we compare their predictive performance with variables from two competing categories, namely macroeconomic and financial variables. The predictive power within and between these three categories is evaluated by applying Dynamic Model Averaging (DMA) which allows for timevarying coefficients and model change. We find that leading indicators have the largest predictive power. Macroeconomic variables, in contrast, are weak predictors as they are even not able to outperform a benchmark AR model, while financial variables are clearly inferior in terms of their predictive power compared to leading indicators. We show that the best set of predictors, within and between categories, changes over time and depends on the forecast horizon. Furthermore, allowing for time-varying model size is especially crucial after the Great Recession.
    Keywords: forecasting,industrial production,model averaging,leading indicator,time-varying parameter
    JEL: C11 C52 E23 E27
    Date: 2020
  5. By: Oscar Claveria (AQR-IREA, University of Barcelona, 08034 Barcelona, Spain.); Ivana Lolic (University of Zagreb, Faculty of Economics and Business); Enric Monte (Department of Signal Theory and Communications, Polytechnic University of Catalunya.); Petar Soric (University of Zagreb, Faculty of Economics and Business)
    Abstract: In this study we construct quarterly consumer confidence indicators of unemployment for the euro area using as input the consumer expectations for sixteen socio-demographic groups elicited from the Joint Harmonised EU Consumer Survey. First, we use symbolic regressions to link unemployment rates to qualitative expectations about a wide range of economic variables. By means of genetic programming we obtain the combination of expectations that best tracks the evolution of unemployment for each group of consumers. Second, we test the out-of-sample forecasting performance of the evolved expressions. Third, we use a state-space model with time-varying parameters to identify the main macroeconomic drivers of unemployment confidence and to evaluate whether the strength of the interplay between variables varies across the economic cycle. We analyse the differences across groups, obtaining better forecasts for respondents comprised in the first quartile with regards to the income of the household and respondents with at least secondary education. We also find that the questions regarding expected major purchases over the next 12 months and savings at present are by far, the variables that most frequently appear in the evolved expressions, hinting at their predictive potential to track the evolution of unemployment. For the economically deprived consumers, the confidence indicator seems to evolve independently of the macroeconomy. This finding is rather consistent throughout the economic cycle, with the exception of stock market returns, which governed unemployment confidence in the pre-crisis period.
    Keywords: Unemployment, Expectations, Consumer behaviour, Forecasting, Genetic programming, State-space models yield. JEL classification: C51, C53, C55, D12, E24, E27, J10
    Date: 2020–01
  6. By: Maziar Sahamkhadam; Andreas Stephan
    Abstract: We employ and examine vine copulas in modeling symmetric and asymmetric dependency structures and forecasting financial returns. We analyze the asset allocations performed during the 2008-2009 financial crisis and test different portfolio strategies such as maximum Sharpe ratio, minimum variance, and minimum conditional Value-at-Risk. We then specify the regular, drawable, and canonical vine copulas, such as the Student-t, Clayton, Frank, Joe, Gumbel, and mixed copulas, and analyze both in-sample and out-of-sample portfolio performances. Out-of-sample portfolio back-testing shows that vine copulas reduce portfolio risk better than simple copulas. Our econometric analysis of the outcomes of the various models shows that in terms of reducing conditional Value-at-Risk, D-vines appear to be better than R- and C-vines. Overall, we find that the Student-t drawable vine copula models perform best with regard to risk reduction, both for the entire period 2005-2012 as well as during the financial crisis.
    Date: 2019–12
  7. By: Vlastakis, Nikolaos; Triantafyllou, Athanasios; Kellard, Neil
    Abstract: In this paper we empirically examine the impact of oil price uncertainty shocks on US stock market volatility. We define the oil price uncertainty shock as the unanticipated component of oil price fluctuations. We find that our oil price uncertainty factor is the most significant predictor of stock market volatility when compared with various observable oil price and volatility measures commonly used in the literature. Moreover, we find that oil price uncertainty is a common volatility forecasting factor of S&P500 constituents, and it outperforms lagged stock market volatility and the VIX when forecasting volatility for medium and long-term forecasting horizons. Interestingly, when forecasting the volatility of S&P500 constituents, we find that the highest predictive power of oil price uncertainty is for the stocks which belong to the financial sector. Overall, our findings show that financial stability is significantly damaged when the degree of oil price unpredictability rises, while it is relatively immune to observable fluctuations in the oil market.
    Keywords: Stock market, Oil, Uncertainty, Realized Variance, Volatility
    Date: 2020–01–22
  8. By: George Athanasopoulos; Nikolaos Kourentzes
    Abstract: The aim of this note is to provide a thinking road-map and a practical guide to researchers and practitioners working on hierarchical forecasting problems. Evaluating the performance of hierarchical forecasts comes with new challenges stemming from both the statistical structure of the hierarchy and the application context. We discuss four relevant dimensions for researchers and analysts: the scale and units of time series, the issue of sparsity, the decision context and the importance of multiple evaluation windows. We conclude with a series of practical recommendations.
    Keywords: aggregation, coherence, hierarchical time series, reconciliation.
    JEL: C18 C53 C55
    Date: 2020
  9. By: Florian Huber; Michael Pfarrhofer; Philipp Piribauer
    Abstract: This paper develops a dynamic factor model that uses euro area (EA) country-specific information on output and inflation to estimate an area-wide measure of the output gap. Our model assumes that output and inflation can be decomposed into country-specific stochastic trends and a common cyclical component. Comovement in the trends is introduced by imposing a factor structure on the shocks to the latent states. We moreover introduce flexible stochastic volatility specifications to control for heteroscedasticity in the measurement errors and innovations to the latent states. Carefully specified shrinkage priors allow for pushing the model towards a homoscedastic specification, if supported by the data. Our measure of the output gap closely tracks other commonly adopted measures, with small differences in magnitudes and timing. To assess whether the model-based output gap helps in forecasting inflation, we perform an out-of-sample forecasting exercise. The findings indicate that our approach yields superior inflation forecasts, both in terms of point and density predictions.
    Date: 2020–01
  10. By: Francis X. Diebold; Glenn D. Rudebusch
    Abstract: The downward trend in Arctic sea ice is a key factor determining the pace and intensity of future global climate change; moreover, declines in sea ice can have a wide range of additional environmental and economic consequences. Based on several decades of satellite data, we provide statistical forecasts of Arctic sea ice extent during the rest of this century. The best-fitting statistical model indicates that sea ice is diminishing at an increasing rate. By contrast, average projections from the CMIP5 global climate models foresee a gradual slowing of sea ice loss even in high carbon emissions scenarios. Our long-range statistical projections also deliver probability assessments of the timing of an ice-free Arctic. This analysis indicates almost a 60 percent chance of an effectively ice-free Arctic Ocean in the 2030s -- much earlier than the average projection from global climate models.
    Date: 2019–12

This nep-for issue is ©2020 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.