|
on Forecasting |
| By: | Christian Buelens |
| Abstract: | This paper analyses how euro area inflation forecasts have been affected by the financial and economic crisis. Its first objective is to evaluate the accuracy of three representative groups of inflation forecasting models (rules of thumb and benchmark models; autoregressive moving average models; autoregressive distributed lag models) under a direct and an indirect approach, respectively. The second objective of the paper is to study how the absolute and relative forecasting performances of the models and approaches have been impacted by the economic and financial crisis. The paper finds that direct forecasting models selected on the basis of a penalty function generally dominate simple benchmark models. The analysis furthermore suggests that when an appropriate specification for the component-specific models is found, indirect forecasts outperform the corresponding direct forecasts. Nonetheless, in line with the findings from earlier studies, there are insufficient elements to assert a systematic superiority of one of the two approaches. Concerning the second objective, the across-the-board rise in the forecast errors of all models considered, confirms that inflation forecasting has become substantially more difficult after the onset of the crisis. However, the deterioration of the different models has been uneven: indeed, direct autoregressive distributed lag models and indirect models improved in relative terms during the crisis. |
| JEL: | C32 C52 C53 E31 E37 E58 |
| Date: | 2012–03 |
| URL: | http://d.repec.org/n?u=RePEc:euf:ecopap:0451&r=for |
| By: | Claudia FORONI; Massimiliano MARCELLINO |
| Abstract: | Forecast models that take into account unbalanced datasets have recently attracted substantial attention. In this paper, we focus on different methods pro- posed so far in the literature to deal with mixed-frequency and ragged-edge datasets: bridge equations, mixed-data sampling (MIDAS), and mixed-frequency (MF) models. We discuss their performance on now- and forecasting the quarterly growth rate of Euro area GDP and its components, using a very large set of monthly indicators taken from Eurostat dataset of Principal European Economic Indicators (PEEI). We both investigate the behavior of single indicator models and combine first the forecasts within each class of models and then the information in the dataset by means of factor models, in a pseudo real-time framework. Anticipating some of the results, MIDAS without an AR component performs worse than the corresponding approach which incorporates it, and MF-VAR seems to outperform the MIDAS approach only at longer horizons. Bridge equations have overall a good performance. Pooling many indicators within each class of models is overall superior to most of the single indicator models. Pooling information with the use of factor models gives even better results, at least at short horizons. A battery of robustness checks high- lights the importance of monthly information during the crisis more than in stable periods. Extending the analysis to a real-time context highlights that revisions do not influence substantially the results. |
| Keywords: | mixed-frequency data; mixed-frequency VAR; MIDAS; factor models; nowcasting; forecasting |
| JEL: | E37 C53 |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:eui:euiwps:eco2012/07&r=for |
| By: | Clemens J.M. Kool; Daniel L. Thornton |
| Abstract: | In this paper, we use survey forecasts to investigate the impact of forward guidance on the predictability of future short- and long-term interest rates in four countries: New Zealand, Norway, Sweden, and the United States. New Zealand began providing forward guidance in 1997, Norway in 2005, and Sweden in 2007. The United States had two periods of implicit forward guidance: 2003-2005 and 2008-2011. Overall, we find little or no convincing evidence that forward guidance actually improves markets' ability to forecast future rates or that any improvement in forecasting short-term rates is reflected in longer-term yields. The weak support we do find is at the short end of the yield curve and at relatively short forecast horizons and only for Norway and Sweden. There is no evidence that forward guidance has increased the efficacy of monetary for New Zealand, the country with the longest--15-year--forward guidance history. |
| Keywords: | monetary policy; central bank transparency; interest rates; term structure; forecasting |
| JEL: | E52 E43 E47 |
| Date: | 2012–03 |
| URL: | http://d.repec.org/n?u=RePEc:use:tkiwps:1205&r=for |
| By: | Peter Reinhard HANSEN; Allan TIMMERMANN |
| Abstract: | Out-of-sample tests of forecast performance depend on how a given data set is split into estimation and evaluation periods, yet no guidance exists on how to choose the split point. Empirical forecast evaluation results can therefore be di cult to interpret, particularly when several values of the split point might have been considered. When the sample split is viewed as a choice variable, rather than being fixed ex ante, we show that very large size distortions can occur for conventional tests of predictive accuracy. Spurious rejections are most likely to occur with a short evaluation sample, while conversely the power of forecast evaluation tests is strongest with long out-of-sample periods. To deal with size distortions, we propose a test statistic that is robust to the effect of considering multiple sample split points. Empirical applications to predictability of stock returns and inflation demonstrate that out-of-sample forecast evaluation results can critically depend on how the sample split is determined. |
| Keywords: | C12; C53 |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:eui:euiwps:eco2012/10&r=for |
| By: | Dufresne, Daniel; Vázquez-Abad, Felisa |
| Abstract: | The classical cobweb theorem is extended to include production lags and price forecasts. Price forecasting based on a longer period has a stabilizing effect on prices. Longer production lags do not necessarily lead to unstable prices; very long lags lead to cycles of constant amplitude. The classical cobweb requires elasticity of demand to be greater than that of supply; this is not necessarily the case in a more general setting, price forecasting has a stabilizing effect. Random shocks are also considered. -- |
| Keywords: | Cobweb theorem,production lags,stable markets,price fluctuations |
| JEL: | C02 C62 C65 D58 E32 |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:ifwedp:201217&r=for |
| By: | Edouard Djeutem (Simon Fraser University); Ken Kasa (Simon Fraser University) |
| Abstract: | This paper studies exchange rate volatility within the context of the monetary model of exchange rates. We assume agents regard this model as merely a benchmark, or reference model, and attempt to construct forecasts that are robust to model misspecification. We show that revisions of robust forecasts are more volatile than revisions of nonrobust forecasts, and that empirically plausible concerns for model misspecification can easily explain observed exchange rate volatility. |
| Keywords: | Exchange rates; Volatility; Robustness |
| JEL: | F31 D81 |
| Date: | 2012–03 |
| URL: | http://d.repec.org/n?u=RePEc:sfu:sfudps:dp12-01&r=for |
| By: | Clements, Michael P. (University of Warwick, Department of Economics) |
| Abstract: | The recent literature has suggested that macroeconomic forecasters may have asymmetric loss functions, and that there may be heterogeneity across forecasters in the degree to which they weigh under and over-predictions. Using an individual-level analysis that exploits the SPF respondents’ histogram forecasts, we find little evidence of asymmetric loss for the in‡ation forecasters. Key words: Disagreement ; forecast uncertainty ; asymmetric loss ; Survey of Professional Forecasters JEL Classification: C53 ; E31 ; E37 |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:wrk:warwec:986&r=for |
| By: | Andrea Carriero; Todd E. Clark; Massimiliano Marcellino |
| Abstract: | The estimation of large vector autoregressions with stochastic volatility using standard methods is computationally very demanding. In this paper we propose to model conditional volatilities as driven by a single common unobserved factor.> This is justified by the observation that the pattern of estimated volatilities in empirical analyses is often very similar across variables. Using a combination of a standard natural conjugate prior for the VAR coefficients and an independent prior on a common stochastic volatility factor, we derive the posterior densities for the parameters of the resulting BVAR with common stochastic volatility (BVAR-CSV). Under the chosen prior, the conditional posterior of the VAR coefficients features a Kroneker structure that allows for fast estimation, even in a large system. Using US and UK data, we show that, compared to a model with constant volatilities, our proposed common volatility model significantly improves model fit and forecast accuracy. The gains are comparable to or as great as the gains achieved with a conventional stochastic volatility specification that allows independent volatility processes for each variable. But our common volatility specification greatly speeds computations. |
| Keywords: | Economic forecasting ; Bayesian statistical decision theory ; Econometric models ; Estimation theory |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedcwp:1206&r=for |
| By: | Andrea CARRIERO; Todd E. CLARK; Massimiliano MARCELLINO |
| Abstract: | The estimation of large Vector Autoregressions with stochastic volatility using standard methods is computationally very demanding. In this paper we propose to model conditional volatilities as driven by a single common unobserved factor. This is justified by the observation that the pattern of estimated volatilities in empirical analyses is often very similar across variables. Using a combination of a standard natural conjugate prior for the VAR coefficients, and an independent prior on a common stochastic volatility factor, we derive the posterior densities for the parameters of the resulting BVAR with common stochastic volatility (BVAR-CSV). Under the chosen prior the conditional posterior of the VAR coefficients features a Kroneker structure that allows for fast estimation, even in a large system. Using US and UK data, we show that, compared to a model with constant volatilities, our proposed common volatility model significantly improves model fit and forecast accuracy. The gains are comparable to or as great as the gains achieved with a conventional stochastic volatility specification that allows independent volatility processes for each variable. But our common volatility specification greatly speeds computations. |
| Keywords: | Bayesian VARs; stochastic volatility; forecasting; prior specification |
| JEL: | C11 C13 C33 C53 |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:eui:euiwps:eco2012/08&r=for |
| By: | Balázs Égert |
| Abstract: | This paper addresses difficulties in modelling exchange rates in South Africa. Real exchange rate models of earlier research seem to be sensitive to the sample period considered, alternative variable definition, data frequency and estimation methods. Alternative exchange rate models proposed in this paper including the stock-flow approach and variants of the monetary model are not fully robust to data frequency and alternative estimation periods, either. Nevertheless, adding openness to the stock-flow approach and augmenting the monetary model with share prices and the country risk premium improves significantly the fit of the models around the large (nominal and real) depreciation episodes of 2002 and 2008. Interestingly, real commodity prices do not help explain the large depreciations. While these models do a reasonably good job in-sample, their out-of-sample forecasting properties remain poor. |
| Keywords: | exchange rate, real exchange rate, nominal exchange rate, commodity, Balassa-Samuelson, productivity, monetary model, stock-flow approach, openness, country risk |
| JEL: | E31 F31 O11 P17 |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:drm:wpaper:2012-18&r=for |
| By: | Müller-Plantenberg, Nikolas (Departamento de Análisis Económico (Teoría e Historia Económica). Universidad Autónoma de Madrid.) |
| Abstract: | Monetary models of exchange rates tend to focus on inflation differentials to explain exchange rate movements. This paper assesses the ability of currency flows to predict exchange rate changes. The focus is on Japan. Currency flows are assumed to depend on the level of the current account and on the international investment position, where the latter is used as a proxy for international debt repayments. A state space model is used to predict simultaneously the exchange rate and its determinants. Using rolling regressions and out-of-sample predictions, it is shown that a model featuring currency flows can predict the direction of exchange rate movements better than a random walk (with or without drift). However, as happens with standard macroeconomic models, the model is not able to outperform a random walk in terms of the mean square prediction error criterion. |
| Keywords: | balance of payments flows, international investment position, exchange rate prediction, out-of-sample prediction, random walk. |
| JEL: | F31 F32 F34 F37 C22 C53 |
| Date: | 2012–03 |
| URL: | http://d.repec.org/n?u=RePEc:uam:wpaper:201209&r=for |
| By: | Albers, Scott; Albers, Andrew |
| Abstract: | In Part One of this paper we use the harmonic analogy of a musical octave to analyze mathematic ratios of U.S. real GNP. These ratios are generated by bringing together figures for U.S. real GNP over intervals of time – “spreads of years” – as numerator and denominator in a single fraction. Using a range of 7-year to 18-year “spreads,” we find that this approach provides strong evidence that American economic history is composed of four 14-year quarter-cycles within a 56 year circuit in the real GNP of the United States, 1869-2007. These periods correlate closely with analysis by Nickolai Kondratiev and provide a framework for predicting an annual steady state rate of growth for the United States falling between 3.4969% and 3.4995% per year. In Part Two of this paper we provide three postscripts including: (1) correlations / speculations on the political and social consequences of this model, (2) simplification / expansion of the geometries implied and (3) analysis / prediction based upon this approach, as concluded by a brief afterword. These post-script refinements narrow the steady state rate of growth predicted to between 3.4969% and 3.4973% per year correlating closely with the 3.4971% rate for annualized quarterly data calculated for Okun’s Law, 1947-2007. The size and interconnectedness of world economies, and the virtually exact correlations provided herein, suggest that the dates predicted for future crises will see changes which are unexpectedly global, dramatic and fierce. |
| Keywords: | Real GNP; Golden Mean; Phi; Long Wave; Kondratiev Wave; Global Financial Crisis; Constitutional Law; American Economic History; Revolution; Consolidation; GNP Spiral; Okun’s Law; “The Great Moderation;” Constitutional Amendments; Steady-state Rate of Growth |
| JEL: | N10 O40 A10 E60 B15 O11 C53 E27 C02 Z0 B16 K19 B59 E37 B41 |
| Date: | 2012–03–30 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:37771&r=for |
| By: | Zal\'an Forr\'o; Peter Cauwels; Didier Sornette |
| Abstract: | On December 16th, 2011, Zynga, the well-known social game developing company went public. This event followed other recent IPOs in the world of social networking companies, such as Groupon or Linkedin among others. With a valuation close to 7 billion USD at the time when it went public, Zynga became one of the biggest web IPOs since Google. This recent enthusiasm for social networking companies raises the question whether they are overvalued. Indeed, during the few months since its IPO, Zynga showed significant variability, its market capitalization going from 5.6 to 10.2 billion USD, hinting at a possible irrational behavior from the market. To bring substance to the debate, we propose a two-tiered approach to compute the intrinsic value of Zynga. First, we introduce a new model to forecast its user base, based on the individual dynamics of its major games. Next, we model the revenues per user using a logistic function, a standard model for growth in competition. This allows us to bracket the valuation of Zynga using three different scenarios: 3.4, 4.0 and 4.8 billion USD in the base case, high growth and extreme growth scenario respectively. This suggests that Zynga has been overpriced ever since its IPO. Given our diagnostic of a bubble, trading strategies should be tuned to capture the sentiments and herding spirits associated with social networks, while minimizing the impact of standard fundamental factors. |
| Date: | 2012–04 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1204.0350&r=for |