nep-for New Economics Papers
on Forecasting
Issue of 2014‒12‒08
ten papers chosen by
Rob J Hyndman
Monash University

  1. Coupling high-frequency data with nonlinear models in multiple-step-ahead forecasting of energy markets' volatility By Jozef Baruník; Tomáš Køehlík
  2. On the Sources of Uncertainty in Exchange Rate Predictability By Joseph P. Byrne; Dimitris Korobilis; Pinho J. Ribeiro
  3. Estimation and Forecasting of Large Realized Covariance Matrices and Portfolio Choice By Laurent Callot; Anders B. Kock; Marcelo C. Medeiros
  4. Marginalized predictive likelihood comparisons of linear Gaussian state-space models with applications to DSGE, DSGEVAR, and VAR models By Warne, Anders; Coenen, Günter; Christoffel, Kai
  5. Assessing Point Forecast Accuracy by Stochastic Error Distance By Francis X. Diebold; Minchul Shin
  6. Optimal Portfolio Choice under Decision-Based Model Combinations By Davide Pettenuzzo; Francesco Ravazzolo
  7. Essential econometric methods of forecasting agricultural commodity prices By Hamulczuk, Mariusz; Grudkowska, Sylwia; Gędek, Stanisław; Klimkowski, Cezary; Stańko, Stanisław
  8. Predicting Financial Stress Events: A Signal Extraction Approach By Ian Christensen; Fuchun Li
  9. Global Variance Risk Premium and Forex Return Predictability By Aloosh, Arash
  10. "Conditional AIC under Covariate Shift with Application to Small Area Prediction" By Yuki Kawakubo; Shonosuke Sugasawa; Tatsuya Kubokawa

  1. By: Jozef Baruník (Institute of Economic Studies, Faculty of Social Sciences, Charles University in Prague, Smetanovo nábreží 6, 111 01 Prague 1, Czech Republic; Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic, Pod Vodarenskou Vezi 4, 182 00, Prague, Czech Republic); Tomáš Køehlík (Institute of Economic Studies, Faculty of Social Sciences, Charles University in Prague, Smetanovo nábreží 6, 111 01 Prague 1, Czech Republic; Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic, Pod Vodarenskou Vezi 4, 182 00, Prague, Czech Republic)
    Abstract: In the past decade, the popularity of realized measures and various linear models for volatility forecasting has attracted attention in the literature on the price variability of energy markets. However, results that would guide practitioners to a specic estimator and model when aiming for the best forecasting accuracy are missing. This paper contributes to the ongoing debate with a comprehensive evaluation of multiple-step-ahead volatility forecasts of energy markets using several popular high-frequency measures and forecasting models. To capture the complex patterns hidden to linear models commonly used to forecast realized volatility, this paper also contributes to the literature by coupling realized measures with articial neural networks as a forecasting tool. Forecasting performance is compared across models as well as realized measures of crude oil, heating oil, and natural gas volatility during three qualitatively distinct periods covering the precrisis period, recent global turmoil of markets in 2008, and the most recent post-crisis period. We conclude that coupling realized measures with articial neural networks results in both statistical and economic gains, reducing the tendency to over-predict volatility uniformly during all tested periods. Our analysis favors the median realized volatility, as it delivers the best performance and is a computationally simple alternative for practitioners.
    Keywords: artificial neural networks, realized volatility, multiple-step-ahead forecasts, energy markets
    JEL: C14 C53 G17
    Date: 2014–09
  2. By: Joseph P. Byrne; Dimitris Korobilis; Pinho J. Ribeiro
    Abstract: We analyse the role of time-variation in coe¢ cients and other sources of un- certainty in exchange rate forecasting regressions. Our techniques incorporate the notion that the relevant set of predictors and their corresponding weights, change over time. We Önd that predictive models which allow for sudden, rather than smooth, changes in coe¢ cients signiÖcantly beat the random walk benchmark in out-of-sample forecasting exercise. Using an innovative variance decomposition scheme, we identify uncertainty in coe¢ cientsíestimation and uncertainty about the precise degree of coe¢ cientsívariability, as the main fac- tors hindering modelsíforecasting performance. The uncertainty regarding the choice of the predictor is small.
    Keywords: Instabilities; Exchange Rate Forecasting; Time-Varying Parameter Models; Bayesian Model Averaging; Forecast Combination; Financial Condi- tion Indexes; Bootstrap
    JEL: C53 E44 F37
    Date: 2014–09
  3. By: Laurent Callot (VU University Amsterdam, the Netherlands); Anders B. Kock (Aarhus University, Denmark); Marcelo C. Medeiros (Pontifical Catholic University of Rio de Janeiro, Brasil)
    Abstract: In this paper we consider modeling and forecasting of large realized covariance matrices by penalized vector autoregressive models. We propose using Lasso-type estimators to reduce the dimensionality to a manageable one and provide strong theoretical performance guarantees on the forecast capability of our procedure. To be precise, we show that we can forecast future realized covariance matrices almost as precisely as if we had known the true driving dynamics of these in advance. We next investigate the sources of these driving dynamics for the realized covariance matrices of the 30 Dow Jones stocks and find that these dynamics are not stable as the data is aggregated from the daily to the weekly and monthly frequency. The theoretical performance guarantees on our forecasts are illustrated on the Dow Jones index. In particular, we can beat our benchmark by a wide margin at the longer forecast horizons. Finally, we investigate the economic value of our forecasts in a portfolio selection exercise and find that in certain cases an investor is willing to pay a considerable amount in order get access to our forecasts.
    Keywords: Realized covariance; vector autoregression; shrinkage; Lasso; forecasting; portfolio allocation
    JEL: C22
    Date: 2014–11–13
  4. By: Warne, Anders; Coenen, Günter; Christoffel, Kai
    Abstract: The predictive likelihood is of particular relevance in a Bayesian setting when the purpose is to rank models in a forecast comparison exercise. This paper discusses how the predictive likelihood can be estimated for any subset of the observable variables in linear Gaussian state-space models with Bayesian methods, and proposes to utilize a missing observations consistent Kalman filter in the process of achieving this objective. As an empirical application, we analyze euro area data and compare the density forecast performance of a DSGE model to DSGE-VARs and reduced-form linear Gaussian models.
    Keywords: Bayesian inference,density forecasting,Kalman filter,missing data,Monte Carlo integration,predictive likelihood
    JEL: C11 C32 C52 C53 E37
    Date: 2014
  5. By: Francis X. Diebold (Department of Economics, University of Pennsylvania); Minchul Shin (Department of Economics, University of Pennsylvania)
    Abstract: We propose point forecast accuracy measures based directly on distance of the forecast-error c.d.f. from the unit step function at 0 (\stochastic error distance," or SED). We provide a precise characterization of the relationship between SED and standard predictive loss functions, showing that all such loss functions can be written as weighted SED's. The leading case is absolute-error loss, in which the SED weights are unity, establishing its primacy. Among other things, this suggests shifting attention away from conditional-mean forecasts and toward conditional-median forecasts.
    Keywords: Forecast accuracy, forecast evaluation, absolute-error loss, quadratic loss, squared-error loss
    JEL: C53
    Date: 2014–11–02
  6. By: Davide Pettenuzzo (Brandeis University); Francesco Ravazzolo (Norges Bank, and BI Norwegian Business School)
    Abstract: We propose a novel Bayesian model combination approach where the combination weights depend on the past forecasting performance of the individual models entering the combina- tion through a utility-based objective function. We use this approach in the context of stock return predictability and optimal portfolio decisions, and investigate its forecasting perfor- mance relative to a host of existing combination schemes. We find that our method produces markedly more accurate predictions than the existing model combinations, both in terms of statistical and economic measures of out-of-sample predictability. We also investigate the incremental role of our model combination method in the presence of model instabilities, by considering predictive regressions that feature time-varying regression coefficients and volatil- ity. We find that the gains from using our model combination method increase significantly when we allow for instabilities in the individual models entering the combination.
    Keywords: Bayesian econometrics; Time-varying parameters; Model combinations; Port- folio choice.
    JEL: C11 C22 G11 G12
    Date: 2014–10
  7. By: Hamulczuk, Mariusz; Grudkowska, Sylwia; Gędek, Stanisław; Klimkowski, Cezary; Stańko, Stanisław
    Abstract: Factors determining agricultural commodity prices. Time series forecasting. X-12-ARIMA and TRAMO/SEATS procedures. Causal forecasting methods. Partial equilibrium models of the agricultural sector.
    Keywords: agricultural sector, forecasting methods, agricultural commodity, price, econometrics, global conditions, Research Methods/ Statistical Methods,
    Date: 2013
  8. By: Ian Christensen; Fuchun Li
    Abstract: The objective of this paper is to propose an early warning system that can predict the likelihood of the occurrence of financial stress events within a given period of time. To achieve this goal, the signal extraction approach proposed by Kaminsky, Lizondo and Reinhart (1998) is used to monitor the evolution of a number of economic indicators that tend to exhibit an unusual behaviour in the periods preceding a financial stress event. Based on the individual indicators, we propose three different composite indicators, the summed composite indicator, the extreme composite indicator and the weighted composite indicator. In-sample forecasting results indicate that the three composite indicators are useful tools for predicting financial stress events. The out-of-sample forecasting results suggest that for most countries, including Canada, the weighted composite indicator performs better than the two others across all criteria considered.
    Keywords: Econometric and statistical methods, Financial stability
    JEL: C14 C4 E37 E47 F36 F37 G01 G17
    Date: 2014
  9. By: Aloosh, Arash
    Abstract: In a long-run risk model with stochastic volatility and frictionless markets, I express expected forex returns as a function of consumption growth variances and stock variance risk premiums (VRPs)—the difference between the risk-neutral and statistical expectations of market return variation. This provides a motivation for using the forward-looking information available in stock market volatility indices to predict forex returns. Empirically, I find that stock VRPs predict forex returns at a one-month horizon, both in-sample and out-of-sample. Moreover, compared to two major currency carry predictors, global VRP has more predictive power for currency carry trade returns, bilateral forex returns, and excess equity return differentials.
    Keywords: Global Variance Risk Premium; Excess Foreign Exchange (Forex) Return; Frictionless Markets; Predictability.
    JEL: F31 F37 G15
    Date: 2014–11–19
  10. By: Yuki Kawakubo (Graduate School of Economics, The University of Tokyo); Shonosuke Sugasawa (Graduate School of Economics, The University of Tokyo); Tatsuya Kubokawa (Faculty of Economics, The University of Tokyo)
    Abstract: In this paper, we consider the problem of selecting explanatory variables of fixed effects in linear mixed models under covariate shift, which is the situation that the values of covariates in the predictive model are different from those in the observed model. We construct a variable selection criterion based on the conditional Akaike information introduced by Vaida and Blanchard (2005) and the proposed criterion is generalization of the conditional Akaike information criterion (conditional AIC) in terms of covariate shift. We especially focus on covariate shift in small area prediction and show usefulness of the proposed criterion through simulation studies.
    Date: 2014–10

This nep-for issue is ©2014 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.