|
on Forecasting |
| By: | Kai Christoffel (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Günter Coenen (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Anders Warne (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.) |
| Abstract: | In this paper, we outline a version of the New Area-Wide Model (NAWM) of the euro area designed for use in the (Broad) Macroeconomic Projection Exercises regularly undertaken by ECB/Eurosystem staff. We present estimation results for the NAWM that are obtained by employing Bayesian inference methods and document the properties of the estimated model by reporting its impulse-response functions and forecast-error-variance decompositions, by inspecting the model-based sample moments, and by examining the model’s forecasting performance relative to a number of benchmarks, including a Bayesian VAR. We finally consider several applications to illustrate the potential contributions the NAWM can make to forecasting and policy analysis. JEL Classification: C11, C32, E32, E37. |
| Keywords: | DSGE modelling, open-economy macroeconomics, Bayesian inference, forecasting, policy analysis, euro area. |
| Date: | 2008–09 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20080944&r=for |
| By: | Dominique Guegan (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Panthéon-Sorbonne - Paris I, EEP-PSE - Ecole d'Économie de Paris - Paris School of Economics - Ecole d'Économie de Paris) |
| Abstract: | In this paper we deal with the problem of non-stationarity encountered in a lot of data sets, mainly in financial and economics domains, coming from the presence of multiple seasonnalities, jumps, volatility, distorsion, aggregation, etc. Existence of non-stationarity involves spurious behaviors in estimated statistics as soon as we work with finite samples. We illustrate this fact using Markov switching processes, Stopbreak models and SETAR processes. Thus, working with a theoretical framework based on the existence of an invariant measure for a whole sample is not satisfactory. Empirically alternative strategies have been developed introducing dynamics inside modelling mainly through the parameter with the use of rolling windows. A specific framework has not yet been proposed to study such non-invariant data sets. The question is difficult. Here, we address a discussion on this topic proposing the concept of meta-distribution which can be used to improve risk management strategies or forecasts. |
| Keywords: | Non-stationarity, switching processes, SETAR processes, jumps, forecast, risk management, copula, probability distribution function. |
| Date: | 2008–03 |
| URL: | http://d.repec.org/n?u=RePEc:hal:paris1:halshs-00270708_v1&r=for |
| By: | Gilles Dufrenot (GREQAM - Groupement de Recherche en Économie Quantitative d'Aix-Marseille - Université de la Méditerranée - Aix-Marseille II - Université Paul Cézanne - Aix-Marseille III - Ecole des Hautes Etudes en Sciences Sociales - CNRS : UMR6579); Dominique Guegan (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Panthéon-Sorbonne - Paris I); Anne Peguin-Feissolle (GREQAM - Groupement de Recherche en Économie Quantitative d'Aix-Marseille - Université de la Méditerranée - Aix-Marseille II - Université Paul Cézanne - Aix-Marseille III - Ecole des Hautes Etudes en Sciences Sociales - CNRS : UMR6579) |
| Abstract: | This paper presents a 2-regime SETAR model with different long-memory processes in both regimes. We briefly present the memory properties of this model and propose an estimation method. Such a process is applied to the absolute and squared returns of five stock indices. A comparison with simple FARIMA models is made using some forecastibility criteria. Our empirical results suggest that our model offers an interesting alternative competing framework to describe the persistent dynamics in modeling the returns. |
| Keywords: | SETAR - Long-memory - Stock indices - Forecasting |
| Date: | 2008–04 |
| URL: | http://d.repec.org/n?u=RePEc:hal:paris1:halshs-00185369_v1&r=for |
| By: | Dominique Guegan (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Panthéon-Sorbonne - Paris I, EEP-PSE - Ecole d'Économie de Paris - Paris School of Economics - Ecole d'Économie de Paris) |
| Abstract: | The detection of chaotic behaviors in commodities, stock markets and weather data is usually complicated by large noise perturbation inherent to the underlying system. It is well known, that predictions, from pure deterministic chaotic systems can be accurate mainly in the short term. Thus, it will be important to be able to reconstruct in a robust way the attractor in which evolves the data, if this attractor exists. In chaotic theory, the deconvolution methods have been largely studied and there exist different approaches which are competitive and complementary. In this work, we apply two methods : the singular value method and the wavelet approach. This last one has not been investigated a lot of filtering chaotic systems. Using very large Monte Carlo simulations, we show the ability of this last deconvolution method. Then, we use the de-noised data set to do forecast, and we discuss deeply the possibility to do long term forecasts with chaotic systems. |
| Keywords: | Deconvolution, chaos, SVD, state space method, wavelets method. |
| Date: | 2008–01 |
| URL: | http://d.repec.org/n?u=RePEc:hal:paris1:halshs-00235448_v1&r=for |
| By: | Laurent Ferrara (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Panthéon-Sorbonne - Paris I, DGEI-DAMEP - Banque de France); Thomas Raffinot (CPR-Asset Management - CPR Asset Management) |
| Abstract: | Non-parametric methods have been empirically proved to be of great interest in the statistical literature in order to forecast stationary time series, but very few applications have been proposed in the econometrics literature. In this paper, our aim is to test whether non-parametric statistical procedures based on a Kernel method can improve classical linear models in order to nowcast the Euro area manufacturing industrial production index (IPI) by using business surveys released by the European Commission. Moreover, we consider the methodology based on bootstrap replications to estimate the confidence interval of the nowcasts. |
| Keywords: | Non-parametric, Kernel, nowcasting, bootstrap, Euro area IPI. |
| Date: | 2008–04 |
| URL: | http://d.repec.org/n?u=RePEc:hal:paris1:halshs-00275769_v1&r=for |
| By: | Andrea Carriero (Queen Mary, University of London); George Kapetanios (Queen Mary, University of London); Massimiliano Marcellino (Bocconi University and EUI) |
| Abstract: | The paper provides a proof of consistency of the ridge estimator for regressions where the number of regressors tends to infinity. Such result is obtained without assuming a factor structure. A Monte Carlo study suggests that shrinkage autoregressive models can lead to very substantial advantages compared to standard autoregressive models. An empirical application focusing on forecasting inflation and GDP growth in a panel of countries confirms this finding. |
| Keywords: | Shrinkage, Forecasting |
| JEL: | C13 C22 C53 |
| Date: | 2008–10 |
| URL: | http://d.repec.org/n?u=RePEc:qmw:qmwecw:wp635&r=for |
| By: | Todd E. Clark; Michael W. McCracken |
| Abstract: | Motivated by the common finding that linear autoregressive models often forecast better than models that incorporate additional information, this paper presents analytical, Monte Carlo, and empirical evidence on the effectiveness of combining forecasts from nested models. In our analytics, the unrestricted model is true, but a subset of the coeffcients are treated as being local-to-zero. This approach captures the practical reality that the predictive content of variables of interest is often low. We derive MSE-minimizing weights for combining the restricted and unrestricted forecasts. Monte Carlo and empirical analyses verify the practical e ectiveness of our combination approach. |
| Keywords: | Econometric models ; Economic forecasting |
| Date: | 2008 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedlwp:2008-037&r=for |
| By: | M. Angeles Carnero (Universidad de Alicante); Daniel Peña (Universidad Carlos III de Madrid); Esther Ruiz (Universidad Carlos III de Madrid) |
| Abstract: | The main goal when fitting GARCH models to conditionally heteroscedastic time series is to estimate the underlying volatilities. It is well known that outliers affect the estimation of the GARCH parameters. However, little is known about their effects when estimating volatilities. In this paper, we show that when estimating the volatility by using Maximum Likelihood estimates of the parameters, the biases incurred can be very large even if estimated parameters have small biases. Consequently, we propose to use robust procedures. In particular, a simple robust estimator of the parameters is proposed and shown that its properties are comparable with other more complicated ones available in the literature. The properties of the estimated and predicted volatilities obtained by using robust filters based on robust parameter estimates are analyzed. All the results are illustrated using daily S&P500 and IBEX35 returns. |
| Keywords: | Heteroscedasticity, M-estimator, QML estimator, Robustness, Financial Markets |
| JEL: | C22 |
| Date: | 2008–10 |
| URL: | http://d.repec.org/n?u=RePEc:ivi:wpasad:2008-13&r=for |
| By: | Ricardo Mestre (Corresponding author: European Central Bank, DG Research, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Peter McAdam (European Central Bank, DG Research, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.) |
| Abstract: | We evaluate residual projection strategies in the context of a large-scale macro model of the euro area and smaller benchmark time-series models. The exercises attempt to measure the accuracy of model-based forecasts simulated both out-of-sample and in-sample. Both exercises incorporate alternative residual-projection methods, to assess the importance of unaccounted-for breaks in forecast accuracy and off-model judgment. Conclusions reached are that simple mechanical residual adjustments have a significant impact of forecasting accuracy irrespective of the model in use, ostensibly due to the presence of breaks in trends in the data. The testing procedure and conclusions are applicable to a wide class of models and thus of general interest. JEL Classification: C52, E30, E32, E37. |
| Keywords: | Macro-model, Forecast Projections, Out-of-Sample, In-Sample, Forecast Accuracy, Structural Break. |
| Date: | 2008–10 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20080950&r=for |
| By: | Elena Angelini (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Marta Bańbura (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Gerhard Rünstler (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.) |
| Abstract: | We estimate and forecast growth in euro area monthly GDP and its components from a dynamic factor model due to Doz et al. (2005), which handles unbalanced data sets in an efficient way. We extend the model to integrate interpolation and forecasting together with cross-equation accounting identities. A pseudo real-time forecasting exercise indicates that the model outperforms various benchmarks, such as quarterly time series models and bridge equations in forecasting growth in quarterly GDP and its components. JEL Classification: E37, C53. |
| Keywords: | Dynamic factor models, interpolation, nowcasting. |
| Date: | 2008–10 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20080953&r=for |
| By: | Dominique Guegan (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Panthéon-Sorbonne - Paris I); Cyril Caillault (FORTIS Investments - Fortis investments) |
| Abstract: | Using non-parametric (copulas) and parametric models, we show that the bivariate distribution of an Asian portfolio is not stable along all the period under study. We suggest several dynamic models to compute two market risk measures, the Value at Risk and the Expected Shortfall: the RiskMetric methodology, the Multivariate GARCH models, the Multivariate Markov-Switching models, the empirical histogram and the dynamic copulas. We discuss the choice of the best method with respect to the policy management of bank supervisors. The copula approach seems to be a good compromise between all these models. It permits taking financial crises into account and obtaining a low capital requirement during the most important crises. |
| Keywords: | Value at Risk - Expected Shortfall - Copula - RiskMetrics - Risk management -GARCH models - Switching models. |
| Date: | 2008–03–06 |
| URL: | http://d.repec.org/n?u=RePEc:hal:paris1:halshs-00185374_v1&r=for |
| By: | Ignacio Velez-Pareja; Dary Luz Hurtado Carrasquilla |
| Abstract: | When forecasting financial statements care has to be taken to construct a consistent and correct model. This is not an easy task. Even the most experienced expert in modeling makes mistakes. This is especially relevant when we construct a financial model without plugs and without circularity. In this work we list some common mistakes made while constructing financial models. This list comes from our experience teaching and coaching students in the process of constructing the model and from the professional practice and consulting in finance, especially in firm valuation. The purpose of this work is to help future students and practitioners when doing the job of forecasting financial statements. After the mistakes have been detected and corrected, they might look like silly mistakes, however, everybody knows that it is easy to be very smart after things have happened. When the mismatching appeared they were real huge problems. After many headaches and lots of work they were found and corrected. Today even after we have worked hard in finding out where the mistakes were, we might consider them as ridiculous or even silly mistakes. An additional thought is to consider that the exercise to forecast the financial statements of a firm from the outside is a futile one. A fruitful forecasting work is done when the analyst is an insider or is a consultant with full access to the relevant information. We expect that these thoughts be useful to our students and colleagues and that they avoid mistakes in their academic and professional work. |
| Date: | 2008–10–20 |
| URL: | http://d.repec.org/n?u=RePEc:col:000162:005107&r=for |
| By: | Dominique Guegan (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Panthéon-Sorbonne - Paris I, EEP-PSE - Ecole d'Économie de Paris - Paris School of Economics - Ecole d'Économie de Paris); Justin Leroux (Institute for Applied Economics - HEC MONTRÉAL, CIRPEE - Centre Interuniversitaire sur le Risque, les Politiques Economiques et l'Emploi) |
| Abstract: | We propose a novel methodology for forecasting chaotic systems which is based on the nearest-neighbor predictor and improves upon it by incorporating local Lyapunov exponents to correct for its inevitable bias. Using simulated data, we show that gains in prediction accuracy can be substantial. The general intuition behind the proposed method can readily be applied to other non-parametric predictors. |
| Keywords: | Chaos theory, Lyapunov exponent, logistic map, Monte Carlo simulations. |
| Date: | 2008–02 |
| URL: | http://d.repec.org/n?u=RePEc:hal:paris1:halshs-00259238_v1&r=for |
| By: | Elena Angelini (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Gonzalo Camba-Méndez (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Domenico Giannone (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Gerhard Rünstler (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt am Main, Germany.); Lucrezia Reichlin (London Business School, Regent’s Park, London NW1 4SA, United Kingdom.) |
| Abstract: | This paper evaluates models that exploit timely monthly releases to compute early estimates of current quarter GDP (now-casting) in the euro area. We compare traditional methods used at institutions with a new method proposed by Giannone, Reichlin, and Small (2005). The method consists in bridging quarterly GDP with monthly data via a regression on factors extracted from a large panel of monthly series with different publication lags. We show that bridging via factors produces more accurate estimates than traditional bridge equations. We also show that survey data and other ‘soft’ information are valuable for now-casting. JEL Classification: E52, C33, C53. |
| Keywords: | Forecasting, Monetary Policy, Factor Model, Real Time Data, Large datasets, News. |
| Date: | 2008–10 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20080949&r=for |