nep-for New Economics Papers
on Forecasting
Issue of 2014‒08‒28
six papers chosen by
Rob J Hyndman
Monash University

  1. Jackknife Model Averaging for Quantile Regressions By Xun Lu; Liangjun Su
  2. Unspanned macroeconomic factors in the yield curve By Coroneo, Laura; Giannone, Domenico; Modugno, Michele
  3. A Note on the (continued) Ability of the Yield Curve to Forecast Economic Downturns in South Africa By Ferdi Botha & Gavin Keeton
  4. Asian Development Outlook Suplement (July 2013) By Asian Development Bank (ADB); ; ;
  5. Do Eurozone yield spreads predict recessions? By Schock, Matthias
  6. A fast-forward look at tertiary education attainment in Europe 2020 By Dragomirescu-Gaina, Catalin; Elia, Leandro; Weber, Anke

  1. By: Xun Lu (Department of Finance, Hong Kong University of Science and Technology); Liangjun Su (School of Economics, Singapore Management University, Singapore, 178903)
    Abstract: In this paper we consider the problem of frequentist model averaging for quantile regression (QR) when all the M models under investigation are potentially misspecified and the number of parameters in some or all models is diverging with the sample size n. To allow for the dependence between the error terms and the regressors in the QR models, we propose a jackknife model averaging (JMA) estimator which selects the weights by minimizing a leave-one-out cross-validation criterion function and demonstrate that the jackknife selected weight vector is asymptotically optimal in terms of minimizing the out-of-sample final prediction error among the given set of weight vectors. We conduct Monte Carlo simulations to demonstrate the finite-sample performance of the proposed JMA QR estimator and compare it with other model selection and averaging methods. We find that in terms of out-of-sample forecasting, the JMA QR estimator can achieve significant efficiency gains over the other methods, especially for extreme quantiles. We apply our JMA method to forecast quantiles of excess stock returns and wages.
    Keywords: Final prediction error; High dimensionality; Model averaging; Model selection; Misspecification; Quantile regression
    JEL: C51 C52
    Date: 2014–08
  2. By: Coroneo, Laura (University of York); Giannone, Domenico (LUISS University of Rome); Modugno, Michele (Board of Governors of the Federal Reserve System (U.S.))
    Abstract: In this paper, we extract common factors from a cross-section of U.S. macro-variables and Treasury zero-coupon yields. We find that two macroeconomic factors have an important predictive content for government bond yields and excess returns. These factors are not spanned by the cross-section of yields and are well proxied by economic growth and real interest rates.
    Keywords: Yield curve; government bonds; factor models; forecasting
    JEL: C33 C53 E43 E44 G12
    Date: 2014–07–30
  3. By: Ferdi Botha & Gavin Keeton
    Abstract: In 2002/03 the yield spread falsely signalled a downswing that never materialised. This paper provides two reasons for this false signal. Firstly, while the Reserve Bank never actually officially declared the start of a downswing, by other important measures a downswing did actually occur. It is to this slowing in economic activity at that time that the yield curve pointed. Secondly, short-term interest rates in 2003 were higher than they should have been because of a mistake made in measuring consumer price inflation. Because South Africa had recently introduced an inflation targeting regime, policy interest rates were as a result of this error kept too high for too long. This policy mistake was rectified as soon as the error in the Consumer Price Index was discovered. Thus, the yield curve in 2002/03 pointed to the reality that short-term interest rates were too high and risked pushing the economy into recession. This is demonstrated by the fact that it was a fall in long bond interest rates that cause the yield spread to turn negative, indicating expectations that short-term interest rates would need to be cut – as indeed they were.
    Keywords: Yield spread, forecasting, economic downswings, interest rates, South Africa
    JEL: E32 E37 E43
    Date: 2014
  4. By: Asian Development Bank (ADB); (Economics and Research Department, ADB); ;
    Abstract: The Asian Development Outlook (ADO) envisaged tepid growth in the major industrial economies over the forecast horizon.
    Keywords: Economics, Macroeconomy, Finance, major industrial economies, developing Asia, ADO forecasts
    Date: 2013–07
  5. By: Schock, Matthias
    Abstract: This paper examines the predictive power of the yield spread for GDP growth and recessions in the Eurozone from the 1990s to the recent past. An OLS and probit framework are used. Credit Default Swap (CDS) data on sovereign bonds as a new risk-adjustment method and a direct measure of default risk improve the quality of prediction significantly. Results show that the quality of growth and recession prediction with the commonly used yield spread remains high, as long as Eurozone sovereign default risk biases are considered.
    Keywords: yield curve, CDS spreads, economic activity
    JEL: E37 E43 E44 G1
    Date: 2014–08
  6. By: Dragomirescu-Gaina, Catalin; Elia, Leandro; Weber, Anke
    Abstract: This paper provides an answer to the question of whether Europe will be able to reach its tertiary education target by 2020. Insights into the dynamics of future education attainment and areas for effective policy interventions in the long-run are highlighted. We model the dynamics behind education decisions as a balance between investment and consumption motivations. We use a panel approach and a wide range of statistical tests to insure that model specifications are stable and robust. We find that while Europe is likely to achieve its target, there is a growing divide between best performing countries and low performers.
    Keywords: human capital investment; tertiary education; panel data; forecasting; Europe 2020 strategy
    JEL: C23 C52 C53 J24
    Date: 2014–06–01

This nep-for issue is ©2014 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.