nep-for New Economics Papers
on Forecasting
Issue of 2015‒09‒18
eighteen papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting with Temporal Hierarchies By Athanasopoulos, George; Hyndman, Rob J.; Kourentzes, Nikolaos; Petropoulos, Fotios
  2. Optimal Portfolio Choice under Decision-Based Model Combinations By Davide Pettenuzzo; Francesco Ravazzolo
  3. Rationality and Momentum in Real Estate Investment Forecasts By F. Mouzakis; D. Papastamos; S. Stevenson
  4. The information content of money and credit for US activity By Albuquerque, Bruno; Baumann, Ursel; Seitz, Franz
  5. Credibility of management earnings forecasts and future returns By Norio Kitagawa; Akinobu Shuto
  6. The Out-of-Sample Forecasting Performance of Non-Linear Models of Regional Housing Prices in the US By Mehmet Balcilar; Rangan Gupta; Stephen M. Miller
  7. Empirical Calibration of Adaptive Learning By Michele Berardi; Jaqueson K. Galimberti
  8. Sentiment-Based Predictions of Housing Market Turning Points with Google Trends By M.Alexander Dietzel
  9. Internet Search and Hotel Revenues By P. Das
  10. Tests of Equal Accuracy for Nested Models with Estimated Factors By Goncalves, Silvia; McCracken, Michael W.; Perron, Benoit
  11. The Dynamic Impact of Uncertainty in Causing and Forecasting the Distribution of Oil Returns and Risk By Giovanni Bonaccolto; Massimiliano Caporin; Rangan Gupta
  12. Using Entropic Tilting to Combine BVAR Forecasts with External Nowcasts By Fabian Krüger; Todd E. Clark; Francesco Ravazzolo
  13. Predictable Recoveries By Xiaoming Cai; Wouter Den Haan; Jonathan Pinder
  14. An Alternative Reference Scenario for Global CO2Emissions from Fuel Consumption: An ARFIMA Approach By José M. Belbute; Alfredo Marvão Pereira
  15. Heterogeneous Adaptive Expectations and Coordination in a Learning-to-Forecast Experiment By Colasante, Annarita; Palestrini, Antonio; Russo, Alberto; Gallegati, Mauro
  16. Wave function in economics By Ledenyov, Dimitri O.; Ledenyov, Viktor O.
  17. Simulating Brazilian Electricity Demand Under Climate Change Scenarios By Trotter, Ian Michael; Féres, José Gustavo; Bolkesjø, Torjus Folsland; de Hollanda, Lavínia Rocha
  18. Foundations of the WVU Econometric Input-Output Model By Randall Jackson; Juan Tomas Sayago-Gomez

  1. By: Athanasopoulos, George; Hyndman, Rob J.; Kourentzes, Nikolaos; Petropoulos, Fotios
    Abstract: This paper introduces the concept of Temporal Hierarchies for time series forecasting. A temporal hierarchy can be constructed for any time series by means of non-overlapping temporal aggregation. Predictions constructed at all aggregation levels are combined with the proposed framework to result in temporally reconciled, accurate and robust forecasts. The implied combination mitigates modelling uncertainty, while the reconciled nature of the forecasts results in a unified prediction that supports aligned decisions at different planning horizons: from short-term operational up to long-term strategic planning. The proposed methodology is independent of forecasting models. It can embed high level managerial forecasts that incorporate complex and unstructured information with lower level statistical forecasts. Our results show that forecasting with temporal hierarchies increases accuracy over conventional forecasting, particularly under increased modelling uncertainty. We discuss organisational implications of the temporally reconciled forecasts using a case study of Accident & Emergency departments.
    Keywords: Hierarchical forecasting, temporal aggregation, reconciliation, forecast combination
    JEL: C44 C53
    Date: 2015–08–28
  2. By: Davide Pettenuzzo; Francesco Ravazzolo
    Abstract: We extend the density combination approach of Billio et al. (2013) to feature combination weights that depend on the past forecasting performance of the individual models entering the combination through a utility-based objective function. We apply our model combination scheme to forecast stock returns, both at the aggregate level and by industry, and investigate its forecasting performance relative to a host of existing combination methods. Overall, we find that our combination scheme produces markedly more accurate predictions than the existing alternatives, both in terms of statistical and economic measures of out-of-sample predictability. We also investigate the performance of our model combination scheme in the presence of model instabilities, by considering individual predictive regressions that feature time-varying regression coefficients and stochastic volatility. We find that the gains from using our combination scheme increase significantly when we allow for instabilities in the individual models entering the combination.Length: 61 pages
    Keywords: Bayesian econometrics, Time-varying parameters, Model combinations, Portfolio choice
    Date: 2015–08
  3. By: F. Mouzakis; D. Papastamos; S. Stevenson
    Abstract: This study examines the rationality and momentum in rental and capital value forecasts of commercial real estate investment market in the United Kingdom. The adopted approach employs three dimensional panel data methods, by attributing the time series dimension to the sequential re-issues by a forecaster of a certain target forecast. The empirical method allows a multiplicity of assumptions regarding the covered by the data target time periods, forecast horizons, forecasters or groups of those to be examined with simultaneous use of the overall panel of data, without the need of segmenting the data set. The investigation includes macro-economic attribution factors to the temporary levels of forecast accuracy, such as Gross Domestic Product and the Default Spread. The empirical findings demonstrate that forecasters tend to maintain their biases over subsequent issues of the same target forecast, regardless of the lowering forecasting horizon. The results also indicate that forecasting accuracy is positively correlated with macro-economic conditions at the time of prediction.
    Keywords: Bias; Forecast Errors; Momentum; Property Forecasts
    JEL: R3
    Date: 2015–07–01
  4. By: Albuquerque, Bruno; Baumann, Ursel; Seitz, Franz
    Abstract: We analyse the forecasting power of different monetary aggregates and credit variables for US GDP. Special attention is paid to the influence of the recent financial market crisis. For that purpose, in the first step we use a three-variable single-equation framework with real GDP, an interest rate spread and a monetary or credit variable, in forecasting horizons of one to eight quarters. This first stage thus serves to pre-select the variables with the highest forecasting content. In a second step, we use the selected monetary and credit variables within different VAR models, and compare their forecasting properties against a benchmark VAR model with GDP and the term spread. Our findings suggest that narrow monetary aggregates, as well as different credit variables, comprise useful predictive information for economic dynamics beyond that contained in the term spread. However, this finding only holds true in a sample that includes the most recent financial crisis. Looking forward, an open question is whether this change in the relationship between money, credit, the term spread and economic activity has been the result of a permanent structural break or whether we might go back to the previous relationships. JEL Classification: E41, E52, E58
    Keywords: credit, forecasting, money
    Date: 2015–06
  5. By: Norio Kitagawa (Kobe University); Akinobu Shuto (The University of Tokyo)
    Abstract: This study investigates the effect of managerial discretion over their initial earnings forecasts on future performance. First, by estimating the discretionary portion of initial management earnings forecasts (defined as discretionary forecasts) based on the findings of fundamental analysis research, we find that firms with higher discretionary forecasts are more likely to miss their earnings forecast at the end of the fiscal year and revise their forecasts downward to meet their earnings forecasts for the period, suggesting that forecast management through discretionary forecasting produces less credible management forecasts in terms of ex-post realization. Second, by using the hedge-portfolio test and regression analysis, we find that firms with higher discretionary forecasts earn consistently negative abnormal returns, suggesting that investors do not fully understand the implication of discretionary forecasts for the credibility of management earnings forecasts and thus overprice them at the forecast announcement.
    Date: 2015–07
  6. By: Mehmet Balcilar (Department of Economics, Eastern Mediterranean University); Rangan Gupta (Department of Economics, University of Pretoria); Stephen M. Miller (Department of Economics, University of Nevada and University of Connecticut)
    Abstract: This paper provides out-of-sample forecasts of linear and non-linear models of US and Census regions housing prices. The forecasts include the traditional point forecasts, but also include interval and density forecasts of the housing price distributions. The non-linear smooth-transition autoregressive model outperforms the linear autoregressive model in point forecasts at longer horizons, but the linear autoregressive model dominates the non-linear smooth-transition autoregressive model at short horizons. In addition, we generally do not find major differences in performance for the interval and density forecasts between the linear and non-linear models. Finally, in a dynamic 25-step ex-ante and interval forecasting design, we, once again, do not find major differences between the linear and nonlinear models.
    Keywords: Forecasting, Linear and non-linear models, US and Census housing price indexes
    JEL: C32 R31
  7. By: Michele Berardi (University of Manchester); Jaqueson K. Galimberti (KOF Swiss Economic Institute, ETH Zurich, Switzerland)
    Abstract: Adaptive learning introduces persistence in the evolution of agents’ beliefs over time. For applied purposes this is a convenient feature to help explain why economies present sluggish adjustments towards equilibrium. The pace of learning is directly determined by the gain parameter, which regulates how quickly new information is incorporated into agents’ beliefs. We document renewed empirical calibrations of plausible gain values for adaptive learning applications to macroeconomic data. We cover a broad range of model specifications of applied interest. Our analysis also includes innovative approaches to the endogenous determination of time-varying gains in real-time, and a thorough discussion of the different theoretical interpretations of the learning gain. We also evaluate the merits of different approaches to the gain calibration according to their performance in forecasting macroeconomic variables and in matching survey forecasts. Our results indicate a great degree of heterogeneity in the gain calibrations according to the variable forecasted and the lag length of the model specifications. Calibrations to match survey forecasts are found to be lower than those derived according to the forecasting performance, suggesting some degree of bounded rationality in the speed with which agents update their beliefs.
    Keywords: expectations, forecasting, bounded rationality, real-time, recursive estimation
    JEL: D83 E37
    Date: 2015–08
  8. By: M.Alexander Dietzel
    Abstract: Purpose - Recent research has found significant relationships between internet search volume and real estate markets. This article examines whether Google search volume data can serve as a leading sentiment indicator and is able to predict turning points in the US housing market. One of the main objectives is to find a model which can be used to produce real-time forecasts in practice. Methodology - Starting from eight individual real-estate-related Google search volume indices, a multivariate probit model is derived by following a selection algorithm. The best model is then tested for its in- and out-of-sample forecasting ability. Findings - The results show that the model predicts the direction of monthly price changes correctly with over 89 per cent in-sample and just above 88 per cent in 1 to 4-month out-of-sample forecasts. The out-of-sample tests show that although the Google model is not always accurate in terms of timing, the signals are always correct when it comes to foreseeing an upcoming turning point. Thus, as signals are generated up to six months early, it functions as a satisfactory and timely indicator of future house price changes. Practical Implications - The results suggest that Google data can serve as an early market indicator and that the application of this data set in binary forecasting models can produce useful predictions of upward and downward movements of US house prices, as measured by the Case-Shiller 20-City House Price Index. This implies that real estate forecasters, economists and policy makers should consider incorporating this free and very current data set into their market forecasts or when performing plausibility checks for future investment decisions. Moreover, the results could potentially be of value for traders investing in Case-Shiller House Price futures and options. Originality - This is the first paper to apply Google search query data as a sentiment indicator in binary forecasting models to predict turning points in the housing market.
    Keywords: Forecasting; Google Data; Housing Market; Sentiment; Turning Points
    JEL: R3
    Date: 2015–07–01
  9. By: P. Das
    Abstract: We examine if online information search trends reflect public interest in purchasing hotel rooms. We introduce the trends into univariate forecasting models and conventional structural models of room night stays and occupancy rates. We find that on a monthly frequency, search trends are significantly reflective of future room night stays and occupancy rates after controlling for known determinants of these variables. Inclusion the trends significantly improve the weekly forecasts of the performance fundamentals.
    Keywords: Forecasting; Google Searches; Hotel; Rents
    JEL: R3
    Date: 2015–07–01
  10. By: Goncalves, Silvia (Western University, Canada); McCracken, Michael W. (Federal Reserve Bank of St. Louis); Perron, Benoit (Université de Montréal, Canada)
    Abstract: In this paper we develop asymptotics for tests of equal predictive ability between nested models when factor-augmented regression models are used to forecast. We provide conditions under which the estimation of the factors does not affect the asymptotic distributions developed in Clark and McCracken (2001) and McCracken (2007). This enables researchers to use the existing tabulated critical values when conducting inference. As an intermediate result, we derive the asymptotic properties of the principal components estimator over recursive windows. We provide simulation evidence on the finite sample effects of factor estimation and apply the tests to the case of forecasting excess returns to the S&P 500 Composite Index.
    Keywords: factor model; out-of-sample forecasts; recursive estimation
    JEL: C12 C32 C38 C52
    Date: 2015–09–14
  11. By: Giovanni Bonaccolto (Department of Statistical Sciences, University of Padova, via C. Battisti 241, 35121 Padova, Italy); Massimiliano Caporin (Department of Economics and Management “Marco Fanno”, University of Padova, via del Santo 33, 35123 Padova, Italy.); Rangan Gupta (Department of Economics, University of Pretoria)
    Abstract: The aim of the work is to analyse the relevance of recently developed news-based measures of economic policy uncertainty and equity market uncertainty in causing and predicting the conditional quantiles and distribution of the crude oil variations, defined both as returns and squared returns. For this purpose, on the one hand, we study the causality relations in quantiles through a nonparametric testing method; on the other hand, we forecast the conditional distribution on the basis of the quantile regression approach and the predictive accuracy is evaluated by means of several suitable tests. Given the presence of structural breaks over time, we implement a rolling window procedure to capture the dynamic relations among the variables.
    Keywords: Granger Causality in Quantiles, Quantile Regression, Forecast of Oil Distribution, Foecast Evaluation
    JEL: C58 C32 C53 Q02
    Date: 2015–09
  12. By: Fabian Krüger; Todd E. Clark; Francesco Ravazzolo
    Abstract: This paper shows entropic tilting to be a flexible and powerful tool for combining mediumterm forecasts from BVARs with short-term forecasts from other sources (nowcasts from either surveys or other models). Tilting systematically improves the accuracy of both point and density forecasts, and tilting the BVAR forecasts based on nowcast means and variances yields slightly greater gains in density accuracy than does just tilting based on the nowcast means. Hence entropic tilting can offer — more so for persistent variables than not-persistent variables — some benefits for accurately estimating the uncertainty of multi-step forecasts that incorporate nowcast information.Length: 42 pages
    Keywords: Forecasting, Prediction, Bayesian Analysis
    Date: 2015–08
  13. By: Xiaoming Cai (Tongji University); Wouter Den Haan (London School of Economics; Centre for Macroeconomics (CFM); Centre for Economic Policy Research (CEPR)); Jonathan Pinder (London School of Economics; Centre for Macroeconomics (CFM))
    Abstract: Should an unexpected change in real GMP of x% lead to an x% change in the forecasts of future GNP? The answer could be no even if GNP is a random walk. We show that US economic downturns often go together with changes in long-term GNP forecasts that are substantially smaller than the initial drop. But not always! Essential for our results is that GNP forecasts are not based on a univariate time series model, which is not uncommon. Our alternative forecasts are based on a simple multivariate representation of GNP's expenditure components.
    Keywords: forecasting, unit root, business cycles
    JEL: C53 E32 E37
    Date: 2015–08
  14. By: José M. Belbute (Department of Economics, University of Évora, Portugal); Alfredo Marvão Pereira (Department of Economics, The College of William and Mary)
    Abstract: We provide alternative reference forecasts for global CO2 emissions based on an ARFIMA model estimated with annual data from 1750 to 2013. These forecasts are free from additional assumptions on demographic and economic variables that are commonly used in reference forecasts, as they only rely on the properties of the underlying stochastic process for CO2emissions, as well as on all the observed information it incorporates. In this sense, these forecasts are more based on fundamentals. Our reference forecast suggests that in 2030, 2040 and 2050, in the absence of any structural changes of any type, CO2 would likely be at about 25%, 34% and 39.9% above 2010 emission levels, respectively. These values are clearly below the levels proposed by other reference scenarios available in the literature. This is important, as it suggests that the ongoing policy goals are actually within much closer reach than what is implied by the standard CO2reference emission scenarios. Having lower and more realistic reference emissions projections not only gives a truer assessment of the policy efforts that are needed, but also highlights the lower costs involved in mitigation efforts, thereby maximizing the likelihood of more widespread energy and environmental policy efforts.
    Keywords: Forecasting, reference scenario, CO2 emissions, long memory, ARFIMA
    JEL: C22 C53 O13 Q47 Q54
    Date: 2015–08–31
  15. By: Colasante, Annarita; Palestrini, Antonio; Russo, Alberto; Gallegati, Mauro
    Abstract: The present work analyzes the individual behavior in an experimental asset market in which the only task of each player is to predict the future price of an asset. To form their expectations, players see the past realization of the asset price in the market and the current information about the mean dividend and the interest rate. We investigate the mechanism of expectation formation in two different contexts: one with a constant fundamental value, and one in which the fundamental price increases over repetitions. Results show that there is heterogeneity both within and between Treatments. Considering an increasing fundamental value has no impact on the individual expectations but it increases the volatility of the market price. We investigate in depth the reasons behind the observed heterogeneity between groups in the same treatment and results show that the heterogeneity of players' expectations is the main cause of the heterogeneity in the realized price. Looking at the coordination, we find out that homogeneous expectations is not a sufficient condition to have high degree of coordination. We analyze the individual forecasting errors as a determinant of the coordination within group and results show that a positive and significant correlation between individual errors strongly influence the level of coordination.
    Keywords: Laboratory experiment, expectations, forecasting, heterogeneity, coordination.
    JEL: C91 C92 D84 G12
    Date: 2015–09–11
  16. By: Ledenyov, Dimitri O.; Ledenyov, Viktor O.
    Abstract: In this research article: 1) the new quantum macroeconomics and microeconomics theories in the quantum econophysics science are formulated, 2) the notion on the wave function in the quantum macroeconomics and microeconomics theories in the quantum econophysics science is introduced, and 3) the quantum econophysical wave equations in the quantum macroeconomics and microeconomics theories in the quantum econophysics science are derived for the first time. Authors show that there is a certain conceptual scientific analogy between 1) the wave functions in the quantum econophysical wave equations in the quantum macroeconomics and microeconomics theories in the quantum econophysics science as well as 2) the wave function in the Schrödinger quantum mechanical wave equation in the quantum mechanics science. The wave function theories are created to make: 1) the economy’s state prediction at the certain time moment, using the wave function in the quantum econophysical wave equation in the quantum macroeconomic theory in the quantum econophysics science; and 2) the firm’s state prediction at the certain time moment, using the wave function in the quantum econophysical wave equation in the quantum microeconomic theory in the quantum econophysics science. Authors use the quantum econophysical wave equations in the quantum econophysics science to develop a new software program for the application by the central / commercial / investment banks with the purpose the make the accurate characterization and forecasting of: 1) the national/global economic performance changes, including the GIP((t), GDP(t), GNP(t) dependences changes, in agreement with the quantum macroeconomics theory in the quantum econophysics science, and 2) the firm’s economic performance changes, including the EBITDA(t) dependence changes in agreement with the quantum microeconomics theory in the quantum econophysics science.
    Keywords: economy’s performance state prediction problem at certain time moment, firm’s performance state prediction problem at the certain time moment, wave functions in quantum econophysical wave equations in quantum macroeconomics/microeconomics theories in quantum econophysics science, wave function in Schrödinger quantum mechanical wave equation in quantum mechanics science, econophysics, econometrics, nonlinear dynamic economic system, economy of scale and scope, macroeconomics, microeconomics.
    JEL: C0 C02 C4 C60 D0 D01 D8 D80 E0 N1 O3
    Date: 2015–09–11
  17. By: Trotter, Ian Michael; Féres, José Gustavo; Bolkesjø, Torjus Folsland; de Hollanda, Lavínia Rocha
    Abstract: Long-term load forecasts are important for planning the development of the electric power infrastructure. We present a methodology for simulating ensembles of daily long-term load forecasts for Brazil under climate change scenarios. For certain applications, it is important to choose an ensemble approach in order to estimate the (conditional) probability distribution of the load. High temporal resolution is necessary in order to preserve key features of the electricity demand that are particularly important in the face of increasing penetration of intermittent renewable power generation.
    Keywords: long-term load forecast, electricity demand, climate change, Demand and Price Analysis, Environmental Economics and Policy, Resource /Energy Economics and Policy, Risk and Uncertainty,
    Date: 2015–09
  18. By: Randall Jackson (Regional Research Institute, West Virginia University); Juan Tomas Sayago-Gomez (Regional Research Institute, West Virginia University)
    Abstract: This document provides an overview of the theoretical foundations and general assumptions of the WVU Econometric Input-Output (ECIO) model. WVU Econometric Input-Output (ECIO) model (hereafter, ECIO model) is a time-series enabled hybrid econometric input-output (IO) model that combines the capabilities of econometric modeling with the strengths of IO modeling. It is designed to facilitate the estimation of economic (specifically, employment and income) impacts of energy technology development, deployment, and operation over a specified forecast period.
    Keywords: input-output model, econometric model, forecasting models
    JEL: R15 C32 E27
    Date: 2015–09

This nep-for issue is ©2015 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.