nep-for New Economics Papers
on Forecasting
Issue of 2014‒09‒29
seven papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting Realized Volatility Using Subsample Averaging By Tae-Hwy Lee; Huiyu Huang
  2. Exchange Rate Predictability in a Changing World By Byrne, Joseph P.; Korobilis, Dimitris; Ribeiro, Pinho J.
  3. Forecasting Equity Premium: Global Historical Average versus Local Historical Average and Constraints By Tae-Hwy Lee; Yundong Tu; Aman Ullah
  4. Forecast combination for U.S. recessions with real-time data By Chen, Cathy W.S.; Gerlach, Richard; Lin, Edward M.H.
  5. Asymmetric Loss in the Greenbook and the Survey of Professional Forecasters By Tae-Hwy Lee; Yiyao Wang
  6. Bond Return Predictability: Economic Value and Links to the Macroeconomy By Davide Pettenuzzo; Antonio Gargano; Allan Timmermann
  7. Penalized Splines, Mixed Models and the Wiener-Kolmogorov Filter By Bloechl, Andreas

  1. By: Tae-Hwy Lee (Department of Economics, University of California Riverside); Huiyu Huang (Grantham, Mayo, Van Otterloo and Company LLC)
    Abstract: When the observed price process is the true underlying price process plus microstructure noise, it is known that realized volatility (RV) estimates will be overwhelmed by the noise when the sampling frequency approaches infinity. Therefore, it may be optimal to sample less frequently, and averaging the less frequently sampled subsamples can improve estimation for quadratic variation. In this paper, we extend this idea to forecasting daily realized volatility. While the subsample-averaging has been proposed and used in estimating RV, this paper is the first that uses the subsample-averaging for forecasting RV. The subsample averaging method we examine incorporates the high frequency data in different levels of systematic sampling. It first pools the high frequency data into several subsamples, that generates forecasts from each subsample, and then combine these forecasts. We find that, in daily S&P 500 return RV forecasts, subsample-averaging generates better forecasts than those using only one subsample without averaging over all subsamples.
    Keywords: Subsample averaging. Forecast combination. High-frequency data. Realized volatility. ARFIMA model. HAR model.
    JEL: C53 C58 G17
    Date: 2014–09
  2. By: Byrne, Joseph P.; Korobilis, Dimitris; Ribeiro, Pinho J.
    Abstract: An expanding literature articulates the view that Taylor rules are helpful in predicting exchange rates. In a changing world however, Taylor rule parameters may be subject to structural instabilities, for example during the Global Financial Crisis. This paper forecasts exchange rates using such Taylor rules with Time Varying Parameters (TVP) estimated by Bayesian methods. In core out-of-sample results, we improve upon a random walk benchmark for at least half, and for as many as eight out of ten, of the currencies considered. This contrasts with a constant parameter Taylor rule model that yields a more limited improvement upon the benchmark. In further results, Purchasing Power Parity and Uncovered Interest Rate Parity TVP models beat a random walk benchmark, implying our methods have some generality in exchange rate prediction.
    Keywords: Exchange Rate Forecasting, Taylor Rules, Time-Varying Parameters, Bayesian Methods,
    Date: 2014
  3. By: Tae-Hwy Lee (Department of Economics, University of California Riverside); Yundong Tu (Peking University, Beijing, China); Aman Ullah (University of California, Riverside)
    Abstract: The equity premium, return on equity minus return on risk-free asset, is expected to be positive. We consider imposing such positivity constraint in local historical average (LHA) in nonparametric kernel regression framework. It is also extended to the semiparametric single index model when multiple predictors are used. We construct the constrained LHA estimator via an indicator function which operates as `model-selection' between the unconstrained LHA and the bound of the constraint (zero for the positivity constraint). We smooth the indicator function by bagging (Breiman 1996a), which operates as `model-averaging' and yields a combined forecast of unconstrained LHA forecasts and the bound of the constraint. The local combining weights are determined by the probability that the constraint is binding. Asymptotic properties of the constrained LHA estimators without and with bagging are established, which show how the positive constraint and bagging can help reduce the asymptotic variance and mean squared errors. Monte Carlo simulations are conducted to show the finite sample behavior of the asymptotic properties. In predicting U.S. equity premium, we show that substantial nonlinearity can be captured by LHA and that the local positivity constraint can improve out-of-sample prediction of the equity premium.
    Keywords: Equity premium; Nonparametric local historical average model; Positivity constraint; Bagging; Model averaging; Semiparametric single index model.
    JEL: C14 C50 C53 G17
    Date: 2014–09
  4. By: Chen, Cathy W.S.; Gerlach, Richard; Lin, Edward M.H.
    Abstract: Methods for Bayesian testing and assessment of dynamic quantile forecasts are proposed. Specifically, Bayes factor analogues of popular frequentist tests for independence of violations from, and for correct coverage of a time series of, quantile forecasts are developed. To evaluate the relevant marginal likelihoods involved, analytic integration methods are utilised when possible, otherwise multivariate adaptive quadrature methods are employed to estimate the required quantities. The usual Bayesian interval estimate for a proportion is also examined in this context. The size and power properties of the proposed methods are examined via a simulation study, illustrating favourable comparisons both overall and with their frequentist counterparts. An empirical study employs the proposed methods, in comparison with standard tests, to assess the adequacy of a range of forecasting models for Value at Risk (VaR) in several financial market data series.
    Keywords: quantile regression; Value-at-Risk; asymmetric-Laplace distribution; Bayes factor; Bayesian Hypothesis testing
    Date: 2014–09–10
  5. By: Tae-Hwy Lee (Department of Economics, University of California Riverside); Yiyao Wang (Booth School of Business, the University of Chicago)
    Abstract: This paper examines forecast rationality of the Greenbook and the Survey of Professional Forecasters (SPF) under asymmetric loss functions, using the method proposed by Elliott, Komunjer and Timmermann (2005) with a rolling window strategy. Over rolling periods, the degree and direction of asymmetry in forecast loss function are time-varying. While rationality under symmetric loss is often rejected, forecast rationality under asymmetric loss is not rejected over nearly all rolling periods. Besides, real output growth is consistently under-predicted in 1990s and inflation rate is consistently over-predicted in 1980s and 1990s. Generally, inflation forecast, especially for long horizon, exhibits greater level of loss asymmetry in magnitude and frequency. The loss asymmetry of real output growth forecast is more pronounced when the last revised vintage data is used rather than real-time vintage is used. All of these results similarly hold in Greenbook and SPF. The results are also similar with different sets of instrumental variables for estimation of the asymmetric loss and for forecast rationality test.
    Keywords: Greenbook, SPF, Asymmetric loss, Forecast rationality, Real output growth forecast, Inflation rate forecast, Real time data, Revised data.
    JEL: C53 E37
    Date: 2014–09
  6. By: Davide Pettenuzzo (International Business School, Brandeis University); Antonio Gargano (University of Melbourne); Allan Timmermann (University of California San Diego)
    Abstract: Studies of bond return predictability ?nd a puzzling disparity between strong statistical evidence of return predictability and the failure to convert return forecasts into economic gains. We show that resolving this puzzle requires accounting for important features of bond return models such as time varying parameters and volatility dynamics. A three-factor model comprising the Fama and Bliss (1987) forward spread, the Cochrane and Piazzesi (2005) com- bination of forward rates and the Ludvigson and Ng (2009) macro factor generates notable gains in out-of-sample forecast accuracy compared with a model based on the expectations hypothesis. Importantly, we ?nd that such gains in predictive accuracy translate into higher risk-adjusted portfolio returns after accounting for estimation error and model uncertainty, as evidenced by the performance of model combinations. Finally, we ?nd that bond excess returns are predicted to be signi?cantly higher during periods with high in?ation uncertainty and low economic growth and that the degree of predictability rises during recessions.
    JEL: G11 G12 G17
    Date: 2014–07
  7. By: Bloechl, Andreas
    Abstract: Penalized splines are widespread tools for the estimation of trend and cycle, since they allow a data driven estimation of the penalization parameter by the incorporation into a linear mixed model. Based on the equivalence of penalized splines and the Hodrick-Prescott filter, this paper connects the mixed model framework of penalized splines to the Wiener- Kolmogorov filter. In the case that trend and cycle are described by ARIMA-processes, this filter yields the mean squarred error minimizing estimations of both components. It is shown that for certain settings of the parameters, a penalized spline within the mixed model framework is equal to the Wiener-Kolmogorov filter for a second fold integrated random walk as the trend and a stationary ARMA-process as the cyclical component.
    Keywords: Hodrick-Prescott filter; mixed models; penalized splines; trend estimation; Wiener-Kolmogorov filter
    JEL: C22 C52
    Date: 2014

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.