|
on Forecasting |
| By: | David F. Hendry (Department of Economics, Oxford University, Manor Rd. Building, Oxford, OX1 3UQ, United Kingdom.); Kirstin Hubrich (Research Department, European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.) |
| Abstract: | To forecast an aggregate, we propose adding disaggregate variables, instead of combining forecasts of those disaggregates or forecasting by a univariate aggregate model. New analytical results show the effects of changing coefficients, mis-specification, estimation uncertainty and mis-measurement error. Forecastorigin shifts in parameters affect absolute, but not relative, forecast accuracies; mis-specification and estimation uncertainty induce forecast-error differences, which variable-selection procedures or dimension reductions can mitigate. In Monte Carlo simulations, different stochastic structures and interdependencies between disaggregates imply that including disaggregate information in the aggregate model improves forecast accuracy. Our theoretical predictions and simulations are corroborated when forecasting aggregate US inflation pre- and post 1984 using disaggregate sectoral data. JEL Classification: C51, C53, E31. |
| Keywords: | Aggregate forecasts, disaggregate information, forecast combination, inflation. |
| Date: | 2010–02 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20101155&r=for |
| By: | Dominique Guegan (Centre d'Economie de la Sorbonne - Paris School of Economics); Justin Leroux (Institute for Applied Economics - HEC Montréal and CIRPEE) |
| Abstract: | We propose a nouvel methodology for forecasting chaotic systems which uses information on local Lyapunov exponents (LLEs) to improve upon existing predictors by correcting for their inevitable bias. Using simulations of the Rössler, Lorenz and Chua attractors, we find that accuracy gains can be substantial. Also, we show that the candidate selection problem identified in Guégan and Leroux (2009a,b) can be solved irrespective of the value of LLEs. An important corrolary follows : the focal value of zero, which traditionally distinguishes order from chaos, plays no role whatsoever when forecasting deterministic systems. |
| Keywords: | Chaos theory, forecasting, Lyapunov exponent, Lorenz attractor, Rössler attractor, Chua attractor, Monte Carlo Simulations. |
| JEL: | C15 C22 C53 C65 |
| Date: | 2010–01 |
| URL: | http://d.repec.org/n?u=RePEc:mse:cesdoc:10019&r=for |
| By: | Christopher J. Neely; David E. Rapach; Jun Tu; Guofu Zhou |
| Abstract: | This paper analyzes the ability of both economic variables and moving-average rules to forecast the monthly U.S. equity premium using out-of-sample tests for 1960?2008. Both approaches provide statistically and economically significant out-of-sample forecasting gains, which are concentrated in U.S. business-cycle recessions. Nevertheless, economic variables and moving-average rules capture different sources of equity premium fluctuations: moving average rules detect the decline in the average equity premium early in recessions, while economic variables more readily pick up the rise in the average equity premium later in recessions. When we simulate data with a habit-formation model characterized by time-varying return volatility and risk aversion relating to business-cycle fluctuations, we find that this model cannot fully account for the out-of-sample forecasting gains in the actual data evidenced by economic variables and moving-average rules. |
| Keywords: | Forecasting ; Stocks |
| Date: | 2010 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedlwp:2010-008&r=for |
| By: | Massimiliano Marcellino (European University Institute, Badia Fiesolana - Via dei Roccettini 9, I-50014 San Domenico di Fiesole (FI), Italy. Bocconi University and CEPR.); Alberto Musso (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.) |
| Abstract: | This paper provides evidence on the reliability of euro area real-time output gap estimates. A genuine real-time data set for the euro area is used, including vintages of several sets of euro area output gap estimates available from 1999 to 2006. It turns out that real-time estimates of the output gap are characterised by a high degree of uncertainty, much higher than that resulting from model and estimation uncertainty only. In particular, the evidence indicates that both the magnitude and the sign of the real-time estimates of the euro area output gap are very uncertain. The uncertainty is mostly due to parameter instability, while data revisions seem to play a minor role. To benchmark our results, we repeat the analysis for the US over the same sample. It turns out that US real time estimates are much more correlated with final estimates than for the euro area, data revisions play a larger role, but overall the unreliability in real time of the US output gap measures detected in earlier studies is confirmed in the more recent period. Moreover, despite some difference across output gap estimates and forecast horizons, the results point clearly to a lack of any usefulness of real-time output gap estimates for inflation forecasting both in the short term (one-quarter and one-year ahead) and the medium term (two-year and three-year ahead). By contrast, some evidence is provided indicating that several output gap estimates are useful to forecast real GDP growth, particularly in the short term, and some appear also useful in the medium run. No single output gap measure appears superior to all others in all respects. JEL Classification: E31, E37, E52, E58. |
| Keywords: | Output gap, real-time data, euro area, inflation forecasts, real GDP forecasts, data revisions. |
| Date: | 2010–02 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20101157&r=for |
| By: | James Mitchell; Garratt, A., Vahey, S.P. |
| Abstract: | We propose a methodology for producing density forecasts for the output gap in real time using a large number of vector autoregessions in inflation and output gap measures. Density combination utilizes a linear mixture of experts framework to produce potentially non-Gaussian ensemble densities for the unobserved output gap. In our application, we show that data revisions alter substantially our probabilistic assessments of the output gap using a variety of output gap measures derived from univariate detrending filters. The resulting ensemble produces well-calibrated forecast densities for US inflation in real time, in contrast to those from simple univariate autoregressions which ignore the contribution of the output gap. Broadening our empirical analysis to consider output gap measures derived from linear time trends, as well as more flexible trends, generates very different point estimates of the output gap. Combining evidence from both linear trends and more flexible univariate detrending filters induces strong multi-modality in the predictive densities for the unobserved output gap. The peaks associated with these two detrending methodologies indicate output gaps of opposite sign for some observations, reflecting the pervasive nature of model uncertainty in our US data. |
| Date: | 2009–10 |
| URL: | http://d.repec.org/n?u=RePEc:nsr:niesrd:342&r=for |
| By: | Sebastian Giesen; Oliver Holtemöller; Juliane Scharff; Rolf Scheufele |
| Abstract: | In this paper we develop a small open economy model explaining the joint determination of output, inflation, interest rates, unemployment and the exchange rate in a multi-country framework. Our model – the Halle Economic Projection Model (HEPM) – is closely related to studies recently published by the International Monetary Fund (global projection model). Our main contribution is that we model the Euro area countries separately. In this version we consider Germany and France, which represent together about 50 percent of Euro area GDP. The model allows for country specific heterogeneity in the sense that we capture different adjustment patterns to economic shocks. The model is estimated using Bayesian techniques. Out-of-sample and pseudo out-of-sample forecasts are presented. |
| Keywords: | Multi-country model, Forecasting, Bayesian estimation |
| JEL: | C32 C53 E37 |
| Date: | 2010–03 |
| URL: | http://d.repec.org/n?u=RePEc:iwh:dispap:6-10&r=for |
| By: | Francesco Audrino; Fulvio Corsi; Kameliya Filipova |
| Abstract: | We propose a simple but effective estimation procedure to extract the level and the volatility dynamics of a latent macroeconomic factor from a panel of observable indicators. Our approach is based on a multivariate conditionally heteroskedastic exact factor model that can take into account the heteroskedasticity feature shown by most macroeconomic variables and relies on an iterated Kalman filter procedure. In simulations we show the unbiasedness of the proposed estimator and its superiority to different approaches introduced in the literature. Simulation results are confirmed in applications to real inflation data with the goal of forecasting long-term bond risk premia. Moreover, we find that the extracted level and conditional variance of the latent factor for inflation are strongly related to NBER business cycles. |
| Keywords: | Macroeconomic variables; Exact factor model; Kalman filter; Heteroskedasticity; Forecasting bond risk premia; Inflation measures; Business cycles |
| JEL: | C13 C33 C53 C82 E31 E47 |
| Date: | 2010–03 |
| URL: | http://d.repec.org/n?u=RePEc:usg:dp2010:2010-09&r=for |
| By: | Mototsugu Shintani (Department of Economics, Vanderbilt University, and Economist, Institute for Monetary and Economic Studies, Bank of Japan (E-mail: mototsugu.shintani@vanderbilt.edu, mototsugu.shintani@boj.or.jp)); Tomoyoshi Yabu (Assistant Professor, Graduate School of Systems and Information Engineering, University of Tsukuba (E-mail: tyabu@sk.tsukuba.ac.jp)); and Daisuke Nagakura (Economist, Institute for Monetary and Economic Studies, Bank of Japan (E-mail: daisuke.nagakura@boj.or.jp)) |
| Abstract: | This paper investigates the spurious effect in forecasting asset returns when signals from technical trading rules are used as predictors. Against economic intuition, the simulation result shows that, even if past information has non predictive power, buy or sell signals based on the difference between the short-period and long-period moving averages of past asset prices can be statistically significant when the forecast horizon is relatively long. The theory implies that both e momentumf and econtrarianf strategies can be falsely supported, while the probability of obtaining each result depends on the type of the test statistics employed. Several modifications to these test statistics are considered for the purpose of avoiding spurious regressions. They are applied to the stock market index and the foreign exchange rate in order to reconsider the predictive power of technical trading rules. |
| Keywords: | Efficient market hypothesis, Nonstationary time series, Random walk, Technical analysis |
| JEL: | C12 C22 C25 G11 G15 |
| Date: | 2008–06 |
| URL: | http://d.repec.org/n?u=RePEc:ime:imedps:08-e-09&r=for |
| By: | Sylvain Leduc; Keith Sill |
| Abstract: | Using survey-based measures of future U.S. economic activity from the Livingston Survey and the Survey of Professional Forecasters, the authors study how changes in expectations, and their interaction with monetary policy, contribute to fluctuations in macroeconomic aggregates. They find that changes in expected future economic activity are a quantitatively important driver of economic fluctuations: a perception that good times are ahead typically leads to a significant rise in current measures of economic activity and inflation. The authors also find that the short-term interest rate rises in response to expectations of good times as monetary policy tightens. Their results provide quantitative evidence on the importance of expectations-driven business cycles and on the role that monetary policy plays in shaping them. |
| Keywords: | Economic forecasting ; Monetary policy ; Business cycles |
| Date: | 2010 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedpwp:10-6&r=for |
| By: | Ivan O. Kitov; Oleg I. Kitov |
| Abstract: | The predictions of the S&P 500 returns made in 2007 have been tested and the underlying models amended. The period between 2003 and 2008 should be described by the dependence of the S&P 500 stock market index on real GDP because the population pyramid was highly inaccurate. The 2008 trough and 2009 rally are well predicted by the original model, however. The rally will end in March/April 2010 and the S&P 500 level will be decreasing into 2011. This prediction should validate the model. |
| Date: | 2010–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1004.0213&r=for |
| By: | Stephen G. Cecchetti; Craig S. Hakkio |
| Abstract: | Transparency is one of the biggest innovations in central bank policy of the past quarter century. Modern central bankers believe that they should be as clear about their objectives and actions as possible. However, is greater transparency always beneficial? Recent work suggests that when private agents have diverse sources of information, public information can cause them to overreact to the signals from the central bank, leading the economy to be too sensitive to common forecast errors. Greater transparency could be destabilizing. While this theoretical result has clear intuitive appeal, it turns on a combination of assumptions and conditions, so it remains to be established that it is of empirical relevance. ; In this paper we study the degree to which increased information about monetary policy might lead to individuals coordinating their forecasts. Specifically, we estimate a series of simple models to measure the impact of inflation targeting on the dispersion of private sector forecasts of inflation. Using a panel data set that includes 15 countries over 20 years we find no convincing evidence that adopting an inflation targeting regime leads to a reduction in the dispersion of private sector forecasts of inflation. While for some specifications adoption of inflation target does seem to reduce the standard deviation of inflation forecasts, the impact is rarely precise and always small. |
| Date: | 2010 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedkrw:rwp10-01&r=for |
| By: | Silvia Lui; James Mitchell; Martin Weale |
| Abstract: | This paper assesses the utility of qualitative expectational survey data at the firm-level in terms of both their ability to anticipate firms’ subsequent retrospective, but qualitative, reports of their performance but also these same firms’ quantitative answers. The assessment requires access to a unique panel dataset which matches firms’ responses to a leading qualitative tendency survey conducted by the Confederation of British Industry with these same firms’ quantitative replies to a different survey carried out by the Office for National Statistics. We employ nonparametric tests of the so-called “best-case scenario” and introduce a weaker test for the coherence between these two surveys and test whether the qualitative data contain a(ny) signal about the quantitative data. We find that while firms’ qualitative expectations are “best-case” predictions of their qualitative assessment of their output growth they do not contain a signal about the quantitative data. But we can reject the null hypothesis of noise for the retrospective qualitative data. We discuss this apparent paradox and suggest that qualitative business survey data are more useful for nowcasting than forecasting. |
| Date: | 2009–10 |
| URL: | http://d.repec.org/n?u=RePEc:nsr:niesrd:343&r=for |