|
on Forecasting |
| By: | Cees Diks (CeNDEF, University of Amsterdam); Valentyn Panchenko (University of New South Wales); Oleg Sokolinskiy (Rutgers Business School); Dick van Dijk (Econometric Institute, Erasmus University Rotterdam) |
| Abstract: | This paper develops a testing framework for comparing the predictive accuracy of copula-based multivariate density forecasts, focusing on a specific part of the joint distribution. The test is framed in the context of the Kullback-Leibler Information Criterion, but using (out-of-sample) conditional likelihood and censored likelihood in order to focus the evaluation on the region of interest. Monte Carlo simulations document that the resulting test statistics have satisfactory size and power properties in small samples. In an empirical application to daily exchange rate returns we find evidence that the dependence structure varies with the sign and magnitude of returns, such that different parametric copula models achieve superior forecasting performance in different regions of the support. Our analysis highlights the importance of allowing for lower and upper tail dependence for accurate forecasting of common extreme appreciation and depreciation of different currencies. |
| Keywords: | Copula-based density forecast; Kullback-Leibler Information Criterion; out-of-sample forecast evaluation |
| JEL: | C12 C14 C32 C52 C53 |
| Date: | 2013–04–19 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:uvatin:20130061&r=for |
| By: | Jon D. Samuels; Rodrigo Sekkel |
| Abstract: | A longstanding finding in the forecasting literature is that averaging forecasts from different models often improves upon forecasts based on a single model, with equal weight averaging working particularly well. This paper analyzes the effects of trimming the set of models prior to averaging. We compare different trimming schemes and propose a new one based on Model Confidence Sets that take into account the statistical significance of historical out-of-sample forecasting performance. In an empirical application of forecasting U.S. macroeconomic indicators, we find significant gains in out-of-sample forecast accuracy from our proposed trimming method. |
| Keywords: | Econometric and statistical methods |
| JEL: | C53 |
| Date: | 2013 |
| URL: | http://d.repec.org/n?u=RePEc:bca:bocawp:13-11&r=for |
| By: | Tom Engsted (Aarhus University and CREATES); Stig V. Møller (Aarhus University and CREATES); Magnus Sander (Aarhus University and CREATES) |
| Abstract: | We document that over the period 1953-2011 US bond returns are predictable in expansionary periods but unpredictable during recessions. This result holds in both in-sample and out-of-sample analyses and using both univariate regressions and combination forecasting techniques. A simulation study shows that our tests have power to reject unpredictability in both expansions and recessions. To judge the economic significance of the results we compute utility gains for a meanvariance investor who takes the predictability patterns into account and show that utility gains are positive in expansions but negative in recessions. The results are also consistent with tests showing that the expectations hypothesis of the term structure holds in recessions but not in expansions. However, the results for bonds are in sharp contrast to results for stocks showing that stock returns are predictable in recessions but not in expansions. Thus, our results indicate that there is not a common predictive pattern of stock and bond returns associated with the state of the economy. |
| Keywords: | Return predictability, expansions and recessions, out-of-sample tests, power properties, mean-variance investor, expectations hypothesis. |
| JEL: | C53 G12 |
| Date: | 2013–04–25 |
| URL: | http://d.repec.org/n?u=RePEc:aah:create:2013-13&r=for |
| By: | Geert Bekaert; Marie Hoerova |
| Abstract: | We decompose the squared VIX index, derived from US S&P500 options prices, into the conditional variance of stock returns and the equity variance premium. The latter is increasing in risk aversion in a wide variety of economic settings. We tackle several measurement issues assessing a plethora of state-of-the-art volatility forecasting models. We then examine the predictive power of the VIX and its two components for stock market returns and economic activity. The variance premium predicts stock returns but the conditional stock market variance predicts economic activity, and is more contemporaneously correlated with financial instability than is the variance premium. |
| JEL: | C22 C52 E32 G12 |
| Date: | 2013–04 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:18995&r=for |
| By: | He, Xue-Zhong; Treich, Nicolas |
| Keywords: | Prediction market, heterogeneous beliefs, risk aversion, favorite-longshot bias, complete markets, and asset prices. |
| Date: | 2012–08–20 |
| URL: | http://d.repec.org/n?u=RePEc:ide:wpaper:27154&r=for |
| By: | Bontemps, Christian |
| Abstract: | In this paper, we develop moment-based tests for parametric discrete distributions. Momentbased test techniques are attractive as they provide easy-to-implement test statistics. We propose a general transformation that makes the moments of interest insensitive to the parameter estimation uncertainty. This transformation is valid in some extended family of non differentiable moments that are of great interest in the case of discrete distributions. We compare this strategy with the one which consists in correcting for the parameter uncertainty considering the power function under local alternatives. The special example of the backtesting of VaR forecasts is treated in detail, and we provide simple moments that have good size and power properties in Monte Carlo experiments. Additional examples considered are discrete counting processes and the geometric distribution. We finally apply our method to the backtesting of VaR forecasts derived from a T-GARCH(1,1) model estimated on foreign exchange rate data. |
| Keywords: | moment-based tests; parameter uncertainty; discrete distributions; Valueat- Risk; backtesting. |
| JEL: | C12 C15 |
| Date: | 2013–04 |
| URL: | http://d.repec.org/n?u=RePEc:ide:wpaper:27109&r=for |
| By: | Maren Brede; ; ; |
| Abstract: | This paper develops a simple New Keynesian model incorporating a small time-varying probability that the economy is struck by a disaster in the future. The model's main prediction is that a small increase in the disaster probability causes a recession in the economy, specically due to limited saving opportunities inasmuch as the model abstracts from capital accumulation. By contrasting its ndings to the ones of a comparable real business cycle model, this paper evaluates how the disaster hypothesis has been used and modelled in the existing literature. |
| Keywords: | time-varying risk, disasters, rare events, nominal rigidities |
| JEL: | E21 E31 E32 |
| Date: | 2013–04 |
| URL: | http://d.repec.org/n?u=RePEc:hum:wpaper:sfb649dp2013-020&r=for |
| By: | Marc Joëts (Ipag Business School and EconomiX-CNRS, University of Paris Ouest, France) |
| Abstract: | This paper proposes to investigate the impact of financialization on energy markets (oil, gas, coal and electricity European forward prices) during both normal times and extreme fluctuation periods through an original behavioral and emotional approach. To this aim, we propose a new theoretical and empirical framework based on a heterogeneous agents model in which fundamentalists and chartists co-exist and are subject to regret and uncertainty. We find significant evidence that energy markets are composed by heterogeneous traders which behave differently depending on the intensity of the price fluctuations and uncertainty context. In particular, energy prices are mainly governed by fundamental and chartist neutral agents during normal times whereas they face to irrational chartist averse investors during extreme fluctuations periods. In this context, the recent energy prices surge can be viewed as the consequence of irrational exhuberance. Our new theoretical model outperforms the random walk in out-of-sample predictive ability. |
| Keywords: | Energy Forward Prices, Financialization, Heterogeneous Agents, Uncertainty Aversion, Regret |
| JEL: | Q43 G15 D81 |
| Date: | 2013–04 |
| URL: | http://d.repec.org/n?u=RePEc:fem:femwpa:2013.32&r=for |
| By: | Katia Berti |
| Abstract: | Stochastic projections are a powerful tool to feature uncertainty in macroeconomic conditions into the analysis of public debt dynamics. They allow simulating a very large number of debt paths, corresponding to as many shock constellations to the non-fiscal determinants of debt evolution (short- and long-term interest rates, growth rate and exchange rate). Furthermore, random shocks are simulated in a way to reflect the size and the correlation of historical shocks. The specific approach for stochastic projections used here, based on the variance-covariance matrix of historical shocks, further allows defining a "central scenario" (for which we use ECFIN's Autumn 2012 forecasts), around which shocks apply. The paper applies this methodology to 24 EU countries over 2013-17. Cross-country differences in the variance of the debt-to-GDP ratio distributions (reflecting differences in historical volatility of macroeconomic conditions) emerge clearly from the simulations. This shows the importance of allowing for a more comprehensive and country-tailored assessment of downward and upward risks to debt dynamics. This stochastic framework also has the distinctive advantage of allowing for an explicit probabilistic assessment of debt projection results. A closer scrutiny of three EU countries in the case with temporary shocks reveals, for instance, that the most likely outcome for IT over 2013-17 is a decreasing path for the debt ratio (though this is projected to be still higher than 116% with a 50% probability in 2017). For ES, simulations show an increasing path over the projection horizon for all shock constellations, with an 80% probability of a debt ratio greater than 100% in 2017. Finally, for HU, we obtain a 60% probability that the debt ratio stabilises or reaches higher values from 2013 onwards, with a 40% probability of a debt ratio greater than 80% in 2017. |
| JEL: | E62 H63 C15 |
| Date: | 2013–04 |
| URL: | http://d.repec.org/n?u=RePEc:euf:ecopap:0480&r=for |