|
on Forecasting |
| By: | Fabio Fornari (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.); Wolfgang Lemke (European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany.) |
| Abstract: | We forecast recession probabilities for the United States, Germany and Japan. The predictions are based on the widely-used probit approach, but the dynamics of regressors are endogenized using a VAR. The combined model is called a ‘ProbVAR’. At any point in time, the ProbVAR allows to generate conditional recession probabilities for any sequence of forecast horizons. At the same time, the ProbVAR is as easy to implement as traditional probit regressions. The slope of the yield curve turns out to be a successful predictor, but forecasts can be markedly improved by adding other financial variables such as the short-term interest rate, stock returns or corporate bond spreads. The forecasting performance is very good for the United States: for the out-of-sample exercise (1995 to 2009), the best ProbVAR specification correctly identifies the ex-post classification of recessions and non-recessions 95% of the time for the one-quarter forecast horizon and 87% of the time for the four-quarter horizon. Moreover, the ProbVAR turns out to significantly improve upon survey forecasts. Relative to the good performance reached for the United States, the ProbVAR forecasts are slightly worse for Germany, but considerably inferior for Japan. JEL Classification: C25, C32, E32, E37. |
| Keywords: | Recessions, forecasting, probit, VAR. |
| Date: | 2010–10 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20101255&r=for |
| By: | Jonsson, Thomas (National Institute of Economic Research); Österholm, Pär (National Institute of Economic Research) |
| Abstract: | In this paper, we evaluate survey-based wage-growth expectations in Sweden. Results show that the expectations are neither unbiased nor efficient forecasts. Evaluating out-of-sample forecasting performance, we find that the survey participants generally perform worse than a con-stant forecast based on reasonable assumptions regarding the inflation target and productivity growth. Our findings indicate that caution should be exercised when relying on these data for policymaking. |
| Keywords: | Survey data; |
| JEL: | E52 J30 |
| Date: | 2010–09 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:nierwp:0121&r=for |
| By: | Pami Dua; Lokendra Kumawat |
| Abstract: | This paper models the univariate dynamics of seasonally unadjusted quarterly macroeconomic time series for the Indian economy including industrial production, money supply (broad and narrow measures) and consumer price index. The seasonal integration-cointegration and the periodic models are employed. The ‘best’ model is selected on the basis of a battery of econometric tests including comparison of out-of sample forecast performance. [Working Paper No. 136] |
| Keywords: | Seasonality, Integration, Periodic Integration, Forecast Performance |
| Date: | 2010 |
| URL: | http://d.repec.org/n?u=RePEc:ess:wpaper:id:3005&r=for |
| By: | Castle, Jennifer L.; Fawcett, Nicholas W.; Hendry, David F. |
| Abstract: | When location shifts occur, cointegration-based equilibrium-correction models (EqCMs) face forecasting problems. We consider alleviating such forecast failure by updating, intercept corrections, differencing, and estimating the future progress of an 'internal' break. Updating leads to a loss of cointegration when an EqCM suffers an equilibrium-mean shift, but helps when collinearities are changed by an 'external' break with the EqCM staying constant. Both mechanistic corrections help compared to retaining a pre-break estimated model, but an estimated model of the break process could outperform. We apply the approaches to EqCMs for UK M1, compared with updating a learning function as the break evolves. |
| JEL: | C1 C53 |
| Date: | 2010–10 |
| URL: | http://d.repec.org/n?u=RePEc:ner:oxford:http://economics.ouls.ox.ac.uk/14904/&r=for |
| By: | Croux, C.; Fried, R.; Gijbels, I.; Mahieu, K. (Tilburg University, Center for Economic Research) |
| Abstract: | This paper proposes a robust forecasting method for non-stationary time series. The time series is modelled using non-parametric heteroscedastic regression, and fitted by a localized MM-estimator, combining high robustness and large efficiency. The proposed method is shown to produce reliable forecasts in the presence of outliers, non-linearity, and heteroscedasticity. In the absence of outliers, the forecasts are only slightly less precise than those based on a localized Least Squares estimator. An additional advantage of the MM-estimator is that it provides a robust estimate of the local variability of the time series. |
| Keywords: | Heteroscedasticity;Non-parametric regression;Prediction;Outliers;Robustness |
| JEL: | C14 C53 |
| Date: | 2010 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:kubcen:2010105&r=for |
| By: | Caporin, M.; McAleer, M.J. |
| Abstract: | This paper focuses on the selection and comparison of alternative non-nested volatility models. We review the traditional in-sample methods commonly applied in the volatility framework, namely diagnostic checking procedures, information criteria, and conditions for the existence of moments and asymptotic theory, as well as the out-of-sample model selection approaches, such as mean squared error and Model Confidence Set approaches. The paper develops some innovative loss functions which are based on Value-at-Risk forecasts. Finally, we present an empirical application based on simple univariate volatility models, namely GARCH, GJR, EGARCH, and Stochastic Volatility that are widely used to capture asymmetry and leverage. |
| Keywords: | volatility model selection;volatility model comparison;non-nested models;model confidence set;Value-at-Risk forecasts;asymmetry, leverage |
| Date: | 2010–10–12 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:eureir:1765020940&r=for |
| By: | Maurizio Bovi (ISAE - Institute for Studies and Economic Analyses) |
| Abstract: | A recent literature questions the mainstream omniscient rational agent, suggesting that agents act as, and have the same bounded rationality of, econometricians. Heterogeneous expectations may then arise because of the different forecasting models used by individuals, who select disparate predictors according to the peculiar net benefits of each model. Net benefits are assumed to be a function of mean square forecasting errors (MSE). Consequently, as in Carroll’s epidemiological approach, an implicit assumption is that the level of disagreement across agents cannot Granger cause model-based MSE. Instead, survey expectations on GDP growth show that the information flow runs exclusively from heterogeneity to MSE. Moreover, variance decompositions point out that survey expectations entropy and MSE are not contemporaneously correlated, enforcing the detected causal chain. Results are robust to several predictors, nonlinearities, and suggest looking also at other possible causes of disagreement. |
| Keywords: | Survey Expectations, Forecasting Models. |
| JEL: | C53 D84 E27 |
| Date: | 2010–01 |
| URL: | http://d.repec.org/n?u=RePEc:isa:wpaper:125&r=for |
| By: | Michael McAleer (Erasmus University Rotterdam, Tinbergen Institute, The Netherlands, and Institute of Economic Research, Kyoto University); Juan-Ángel Jiménez-Martín (Department of Quantitative Economics, Complutense University of Madrid); Teodosio Pérez-Amaral (Department of Quantitative Economics, Complutense University of Madrid) |
| Abstract: | A risk management strategy is proposed as being robust to the Global Financial Crisis (GFC) by selecting a Value-at-Risk (VaR) forecast that combines the forecasts of different VaR models. The robust forecast is based on the median of the point VaR forecasts of a set of conditional volatility models. This risk management strategy is GFC-robust in the sense that maintaining the same risk management strategies before, during and after a financial crisis would lead to comparatively low daily capital charges and violation penalties. The new method is illustrated by using the S&P500 index before, during and after the 2008-09 global financial crisis. We investigate the performance of a variety of single and combined VaR forecasts in terms of daily capital requirements and violation penalties under the Basel II Accord, as well as other criteria. The median VaR risk management strategy is GFC-robust as it provides stable results across different periods relative to other VaR forecasting models. The new strategy based on combined forecasts of single models is straightforward to incorporate into existing computer software packages that are used by banks and other financial institutions. |
| Keywords: | Value-at-Risk (VaR), daily capital charges, robust forecasts, violation penalties, optimizing strategy, aggressive risk management strategy, conservative risk management strategy, Basel II Accord, global financial crisis |
| JEL: | G32 G11 C53 C22 |
| Date: | 2010–10 |
| URL: | http://d.repec.org/n?u=RePEc:kyo:wpaper:727&r=for |
| By: | Croux, C.; Gelper, S.; Mahieu, K. (Tilburg University, Center for Economic Research) |
| Abstract: | This article presents a control chart for time series data, based on the one-step- ahead forecast errors of the Holt-Winters forecasting method. We use robust techniques to prevent that outliers affect the estimation of the control limits of the chart. Moreover, robustness is important to maintain the reliability of the control chart after the occurrence of alarm observations. The properties of the new control chart are examined in a simulation study and on a real data example. |
| Keywords: | Control chart;Holt-Winters;Non-stationary time series;Out- lier detection;Robustness;Statistical process control. |
| JEL: | C44 C53 |
| Date: | 2010 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:kubcen:2010107&r=for |
| By: | McAleer, M.J.; Jimenez-Martin, J-A.; Perez-Amaral, T. |
| Abstract: | A risk management strategy is proposed as being robust to the Global Financial Crisis (GFC) by selecting a Value-at-Risk (VaR) forecast that combines the forecasts of different VaR models. The robust forecast is based on the median of the point VaR forecasts of a set of conditional volatility models. This risk management strategy is GFC-robust in the sense that maintaining the same risk management strategies before, during and after a financial crisis would lead to comparatively low daily capital charges and violation penalties. The new method is illustrated by using the S&P500 index before, during and after the 2008-09 global financial crisis. We investigate the performance of a variety of single and combined VaR forecasts in terms of daily capital requirements and violation penalties under the Basel II Accord, as well as other criteria. The median VaR risk management strategy is GFC-robust as it provides stable results across different periods relative to other VaR forecasting models. The new strategy based on combined forecasts of single models is straightforward to incorporate into existing computer software packages that are used by banks and other financial institutions. |
| Keywords: | Value-at-Risk (VaR);daily capital charges;robust forecasts;violation penalties;optimizing strategy;aggressive risk management strategy;conservative risk management strategy;Basel II Accord;global financial crisis |
| Date: | 2010–10–12 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:eureir:1765020964&r=for |
| By: | Alfaro, Rodrigo; Sagner, Andres |
| Abstract: | In this paper we provide a closed-form expression for one of the most popular index in Technical Analysis: the Relative Strength Index (RSI). Given that we show how the standard binomial model for the stock price can be used to predict RSI. The algorithm is as simple as to code a standard European option. In an empirical application to the Chilean exchange rate we show how the method works having a better out of sample performance than an ARMA(1,1) model. |
| Keywords: | Relative Strength Index; Binomial Model; Financial Forecast |
| JEL: | G14 E37 |
| Date: | 2010–04 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:25913&r=for |
| By: | Antonis A. Michis (Central Bank of Cyprus) |
| Abstract: | Indexes of consumer and business sentiment are frequently characterized by measurement errors and short-term cyclical fluctuations that can distort their predictive accuracy for GDP changes. While measurement errors arise due to the survey sampling procedures that characterize these surveys, short-term cyclical fluctuations are generally linked with various exogenous and irregular factors that are not necessarily related to the economy. This paper shows, using data on the US economy, that applying wavelet denoising on indexes of consumer and business sentiment in the context of the linear regression model can overcome these limitations and can provide: (a) efficient coefficient estimates in models that explain consumer sentiment index variation; and (b) consistent coefficient estimates and predictions in models for GDP changes when using consumer and business sentiment indexes as predictors. |
| Keywords: | Consumer sentiment index, denoised least squares, index of homebuilders’sentiment, index of manufacturing activity, measurement errors. |
| JEL: | C43 C53 C82 |
| Date: | 2010–10 |
| URL: | http://d.repec.org/n?u=RePEc:cyb:wpaper:2010-9&r=for |
| By: | José Valentim Machado Vicente; Osmani Teixeira de Carvalho Guillen |
| Abstract: | There is a widespread belief that inflation-linked bonds are a direct source of information about inflation expectations. In this paper we address this issue by analyzing the relationship between break-even inflation (the difference between nominal and real yields) and future inflation. The dataset is extracted from Brazilian Treasury bonds covering the period from April 2005 to July 2010. We find that break-even inflation is an unbiased forecast only of the 3-month and 6-month ahead inflation. For medium horizons (12 and 18 months) break-even inflation has weak explanatory power of future inflation. Over long horizons (24 and 30 months), we report a significant, but counterintuitive, negative relationship between the break-even and realized inflations. |
| Date: | 2010–10 |
| URL: | http://d.repec.org/n?u=RePEc:bcb:wpaper:214&r=for |
| By: | J. Isaac Miller (Department of Economics, University of Missouri-Columbia); Shawn Ni (Department of Economics, University of Missouri-Columbia) |
| Abstract: | We examine how future real GDP growth relates to changes in the forecasted long-term average of discounted real oil prices and to changes in unanticipated fluctuations of real oil prices around the forecasts. Forecasts are conducted using a state-space oil market model, in which global real economic activity and real oil prices share a common stochastic trend. Changes in unanticipated fluctuations and changes in the forecasted long-term average of discounted real oil prices sum to real oil price changes. We find that these two components have distinctly different relationships with future real GDP growth. Positive and negative changes in the unanticipated fluctuations of real oil prices correlate with asymmetric responses of future real GDP growth. In comparison, changes in the forecasted long-term average are smaller in magnitude but are more influential on real GDP. Persistent upward revisions of forecasts in the 2000s had a substantial negative impact on real GDP growth, according to our estimates.. |
| Keywords: | oil price and the macroeconomy, oil market fundamental, oil price forecasts, Kalman filter |
| JEL: | E31 E32 Q43 |
| Date: | 2010–10–11 |
| URL: | http://d.repec.org/n?u=RePEc:umc:wpaper:1012&r=for |
| By: | V. CAUBERGHE; M. GEUENS; P. DE PELSMACKER |
| Keywords: | demography prediction, demographic targeting, web advertising, Random Forests, web user profiling, clickstream analysis |
| Date: | 2010–09 |
| URL: | http://d.repec.org/n?u=RePEc:rug:rugwps:10/671&r=for |
| By: | Wilfried Rickels; Dennis Görlich; Gerrit Oberst |
| Abstract: | In 2005, the European Emission Trading Scheme (EU-ETS) established a new commodity: the right to emit a ton of CO2 (EUA). Since its launch, the corresponding price has shown rather turbulent dynamics, including nervous reactions to policy announcements and a price collapse after a visible over-allocation in Phase I. As a consequence, the question whether fundamental factors (fossil fuel prices, economic activity, weather) affect the EUA price remained partially unresolved. Today, being halfway through Phase II (2008–2012) and relying on a more mature market, we use more reliable data to investigate the extent to which allowance price dynamics can be explained by market fundamentals. We empirically test for the influence of fuel prices, economic activity, and weather variations. Fuel prices allow to test for fuel switching from coal to gas, the most important short-term abatement option for most installations in the EU-ETS. The empirical results show a significant influence of gas, coal, and oil prices, of economic activity and of some weather variations. When including the relative price of coal to gas on a forward level, we found evidence of a switching effect. Yet, on a spot level the demand effect seems to dominate. However, when including the absolute coal price the coefficient is positive, contradicting theory with respect to both the switching and the demand effect. The significant weather variations suggest that their influence on EUA prices is less driven by their effect on energy demand but more by their effect on the provision of carbon-free renewable energy. Overall, our results show that the price dynamics are much better explained by a model based on fundamentals than by a purely autoregressive model. However, the results also show that fundamentals alone cannot fully explain price dynamics and that forecasting is improved by the inclusion of time series characteristics |
| Keywords: | Carbon emission trading, EU ETS, Carbon price influence factors, Fuel switching |
| JEL: | C22 G14 Q54 |
| Date: | 2010–09 |
| URL: | http://d.repec.org/n?u=RePEc:kie:kieliw:1650&r=for |
| By: | Antonio Bassanetti (Bank of Italy); Michele Caivano (Bank of Italy); Alberto Locarno (Bank of Italy) |
| Abstract: | The aim of the paper is to estimate a reliable quarterly time-series of potential output for the Italian economy, exploiting four alternative approaches: a Bayesian unobserved component method, a univariate time-varying autoregressive model, a production function approach and a structural VAR. Based on a wide range of evaluation criteria, all methods generate output gaps that accurately describe the Italian business cycle over the past three decades. All output gap measures are subject to non-negligible revisions when new data become available. Nonetheless they still prove to be informative about the current cyclical phase and, unlike the evidence reported in most of the literature, helpful at predicting inflation compared with simple benchmarks. We assess also the performance of output gap estimates obtained by combining the four original indicators, using either equal weights or Bayesian averaging, showing that the resulting measures (i) are less sensitive to revisions; (ii) are at least as good as the originals at tracking business cycle fluctuations; (iii) are more accurate as inflation predictors. |
| Keywords: | potential output, business cycle, Phillips curve, output gap |
| JEL: | E37 C52 |
| Date: | 2010–09 |
| URL: | http://d.repec.org/n?u=RePEc:bdi:wptemi:td_771_10&r=for |
| By: | P. BAECKE; D. VAN DEN POEL |
| Abstract: | Nowadays, an increasing number of information technology tools are implemented in order to support decision making about marketing strategies and improve customer relationship management (CRM). Consequently, an improvement in CRM can be obtained by enhancing the databases on which these information technology tools are based. This study shows that data augmentation with situational variables of the purchase occasion can significantly improve purchasing behavior predictions for a home vending company. Three dimensions of situational variables are examined: physical surroundings, temporal perspective and social surroundings respectively represented by weather, time and salesperson variables. The smallest, but still significant, increase in predictive performance was measured by enhancing the model with time variables. Besides the moment of the day, this study shows that the incorporation of weather variables, and more specifically sunshine, can also improve the accuracy of a CRM model. Finally, the best improvement in purchasing behavior predictions was obtained by taking the salesperson effect into account using a multilevel model. |
| Keywords: | Customer relationship management (CRM), data enhancement, multilevel model, situational variables, purchase predictions, home vending, predictive analytics. |
| Date: | 2010–07 |
| URL: | http://d.repec.org/n?u=RePEc:rug:rugwps:10/658&r=for |
| By: | Adrian Pagan (University of Technology, Sydney) |
| Abstract: | There is much scepticism about the ability to predict recessions. Harding and Pagan (2010b)have argued that this is because the definition of a recession involves the signs of future growth rates of economic activity and there is little predictability of these from the past. Turkey represents an interesting case study since growth in Turkish GDP features quite high serial correlation, suggesting that growth itself is predictable. Thus I want to examine whether it is possible to predict recessions in Turkey. As there seems only a small published literature on this it will be necessary to indicate what definition of recession is to be used and what information might be available to make a prediction of such an event. We found that using information from past macroeconomic variables would result in only limited success in predicting Turkish recessions. |
| Keywords: | Conditional CAPM |
| Date: | 2010–10 |
| URL: | http://d.repec.org/n?u=RePEc:koc:wpaper:1027&r=for |