nep-for New Economics Papers
on Forecasting
Issue of 2012‒09‒16
ten papers chosen by
Rob J Hyndman
Monash University

  1. Can macro variables used in stress testing forecast the performance of banks? By Luca Guerrieri; Michelle Welch
  2. Real-time forecasting with a mixed-frequency VAR By Frank Schorfheide; Dongho Song
  3. Real-Time Forecast Density Combinations (Forecasting US GDP Growth Using Mixed-Frequency Data) By Götz Thomas B.; Hecq Alain; Urbain Jean-Pierre
  4. Survey-based nowcasting of US growth: a real-time forecast comparison over more than 40 years By Antonello D’Agostino; Bernd Schnatz
  5. Sometimes it helps: the evolving predictive power of spreads on GDP dynamics By Giulio Nicoletti; Raffaele Passaro
  6. How informative are the subjective density forecasts of macroeconimists? By Geoff Kenny; Thomas Kostka; Federico Masera
  7. The Chicago Fed DSGE model By Scott Brave; Jeffrey R. Campbell; Jonas D. M. Fisher; Alejandro Justiniano
  8. Emerging Market Sovereign Bond Spreads: Estimation and Back-testing By Fabio Comelli
  9. A Flexible Semiparametric Model for Time Series By Degui Li; Oliver Linton; Zudi Lu
  10. The stability of feature selection and class prediction from ensemble tree classifiers. By Paul, Jérôme

  1. By: Luca Guerrieri; Michelle Welch
    Abstract: When stress tests for the banking sector use a macroeconomic scenario, an unstated premise is that macro variables should be useful factors in forecasting the performance of banks. We assess whether variables such as the ones included in stress tests for U.S. bank holding companies help improve out of sample forecasts of chargeoffs on loans, revenues, and capital measures, relative to forecasting models that exclude a role for macro factors. Using only public data on bank performance, we find the macro variables helpful, but not for all measures. Moreover, even our best-performing models imply bands of uncertainty around the forecasts so large as to make it challenging to distinguish the implications of alternative macro scenarios.
    Date: 2012
  2. By: Frank Schorfheide; Dongho Song
    Abstract: This paper develops a vector autoregression (VAR) for macroeconomic time series which are observed at mixed frequencies – quarterly and monthly. The mixed-frequency VAR is cast in state-space form and estimated with Bayesian methods under a Minnesota-style prior. Using a real-time data set, we generate and evaluate forecasts from the mixed-frequency VAR and compare them to forecasts from a VAR that is estimated based on data time-aggregated to quarterly frequency. We document how information that becomes available within the quarter improves the forecasts in real time.
    Keywords: Bayesian statistical decision theory ; Forecasting ; Vector autoregression
    Date: 2012
  3. By: Götz Thomas B.; Hecq Alain; Urbain Jean-Pierre (METEOR)
    Abstract: We combine the issues of dealing with variables sampled at mixed frequencies and the use ofreal-time data. In particular, the repeated observations forecasting (ROF) analysis of Stark andCroushore (2002) is extended to an autoregressive distributed lag setting in which the regressorsmay be sampled at higher frequencies than the regressand. For the US GDP quarterly growth rate, wecompare the forecasting performances of an AR model with several mixed-frequency models amongwhich the MIDAS approach. The additional dimension provided by different vintages allows us tocompute several forecasts for a given calendar date and use them to construct forecast densities.Scoring rules are employed to test for their equality and to construct combinations of them. Giventhe change of the implied weights over time, we propose time-varying ROF-based weights usingvintage data which present an alternative to traditional weighting schemes.
    Keywords: macroeconomics ;
    Date: 2012
  4. By: Antonello D’Agostino (European Financial Stability Facility (EFSF), 43 avenue John F. Kennedy, L-1855 Luxembourg and the Central Bank and Financial Services Authority of Ireland); Bernd Schnatz (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt, Germany)
    Abstract: Reliable and timely information about current economic conditions is crucial for policy makers and expectations formation. This paper demonstrates the efficacy of the Survey of Professional Forecasters (SPF) and the Purchasing Manager Indices (PMI) in anticipating US real economic activity. We conduct a fully-fledged real-time out-ofsample forecasting exercise linking these surveys to US GDP and industrial production growth over a long sample period. We find that both indicators convey valuable information for assessing current economic conditions. The SPF clearly outperforms the PMI in forecasting GDP growth, while it performs quite poorly in anticipating industrial production growth. Combining the information included in both surveys further improves the accuracy of both, the PMI and the SPF-based forecast. JEL Classification: E37, E47, C22, C53
    Keywords: US, business cycle, PMI, forecasting, real time data
    Date: 2012–08
  5. By: Giulio Nicoletti (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt, Germany and Bank of Italy); Raffaele Passaro (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt, Germany)
    Abstract: We investigate the predictive content of credit and government interest spreads with respect to the Italian GDP growth. Our analysis with Dynamic Model Averaging identifies when interest spreads were more useful predictors of economic activity: these periods are not limited to the Great Recession. For credit spreads we gather information from both bank loans and corporate bonds and we compare their predictive role over time and over different forecasting horizons. JEL Classification: C52, E37
    Keywords: GDP forecasting, Bayesian Econometrics, Model Averaging
    Date: 2012–07
  6. By: Geoff Kenny (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt, Germany); Thomas Kostka (European Central Bank, Kaiserstrasse 29, D-60311 Frankfurt, Germany); Federico Masera (Universidad Carlos III de Madrid, Economics Department, C/ Madrid 126, 28903 Getafe (Madrid), España)
    Abstract: In this paper, we propose a framework to evaluate the subjective density forecasts of macroeconomists using micro data from the euro area Survey of Professional Forecasters (SPF). A key aspect of our analysis is the evaluation of the entire predictive densities, including an evaluation of the impact of density features such as location, spread, skew and tail risk on density forecast performance. Overall, we find considerable heterogeneity in the performance of the surveyed densities at the individual level. Relative to a set of simple benchmarks, this performance is somewhat better for GDP growth than for inflation, although in the former case it diminishes substantially with the forecast horizon. In addition, we report evidence of some improvement in the relative performance of expert densities during the recent period of macroeconomic volatility. However, our analysis also reveals clear evidence of overconfidence or neglected risks in expert probability assessments, as reflected in frequent occurrences of events which are assigned a zero probability. Moreover, higher moment features of expert densities, such as skew or the degree of probability mass in their tails, are shown not to contribute significantly to improvements in individual density forecast performance. JEL Classification: C22, C53.
    Keywords: Forecast evaluation, neglected risks, real-time data, Survey of Professional Forecasters.
    Date: 2012–07
  7. By: Scott Brave; Jeffrey R. Campbell; Jonas D. M. Fisher; Alejandro Justiniano
    Abstract: The Chicago Fed dynamic stochastic general equilibrium (DSGE) model is used for policy analysis and forecasting at the Federal Reserve Bank of Chicago. This article describes its specification and estimation, its dynamic characteristics and how it is used to forecast the US economy. In many respects the model resembles other medium scale New Keynesian frameworks, but there are several features which distinguish it: the monetary policy rule includes forward guidance, productivity is driven by neutral and investment specific technical change, multiple price indices identify inflation and there is a financial accelerator mechanism.
    Keywords: Keynesian economics ; Forecasting ; Stochastic analysis
    Date: 2012
  8. By: Fabio Comelli
    Abstract: We estimate sovereign bond spreads of 28 emerging economies over the period January 1998-December 2011 and test the ability of the model in generating accurate in-sample predictions for emerging economies bond spreads. The impact and significance of country-specific and global explanatory variables on bond spreads varies across regions, as well as economic periods. During crisis times, good macroeconomic fundamentals are helpful in containing bond spreads, but less than in non-crisis times, possibly reflecting the impact of extra-economic forces on bond spreads when a financial crisis occurs. For some emerging economies, in-sample predictions of the monthly changes in bond spreads obtained with rolling regression routines are significantly more accurate than forecasts obtained with a random walk. Rolling regression-based bond spread predictions appear to convey more information than those obtained with a linear prediction method. By contrast, bond spreads forecasts obtained with a linear prediction method are less accurate than those obtained with random guessing.
    Date: 2012–08–28
  9. By: Degui Li; Oliver Linton; Zudi Lu
    Abstract: We consider approximating a multivariate regression function by an affine combination of one-dimensional conditional component regression functions. The weight parameters involved in the approximation are estimated by least squares on the first-stage nonparametric kernel estimates. We establish asymptotic normality for the estimated weights and the regression function in two cases: the number of the covariates is finite, and the number of the covariates is diverging. As the observations are assumed to be stationary and near epoch dependent, the approach in this paper is applicable to estimation and forecasting issues in time series analysis. Furthermore, the methods and results are augmented by a simulation study and illustrated by application in the analysis of the Australian annual mean temperature anomaly series. We also apply our methods to high frequency volatility forecasting, where we obtain superior results to parametric methods.
    Keywords: Asymptotic normality, model averaging, Nadaraya-Watson kernel estimation, near epoch dependence, semiparametric method
    JEL: C14 C22
    Date: 2012–08–04
  10. By: Paul, Jérôme
    Abstract: The bootstrap aggregating procedure at the core of ensemble tree classifiers reduces, in most cases, the variance of such models while offering good generalization capabilities. The average predictive performance of those ensembles is known to improve up to a certain point while increasing the ensemble size. The present work studies this convergence in contrast to the stability of the class prediction and the variable selection performed while and after growing the ensemble. Experiments on several biomedical datasets, using random forests or bagging of decision trees,show that class prediction and, most notably, variable selection typically require orders of magnitude more trees to get stable.
    Date: 2012

This nep-for issue is ©2012 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.