nep-ets New Economics Papers
on Econometric Time Series
Issue of 2017‒10‒08
eleven papers chosen by
Yong Yin
SUNY at Buffalo

  1. Inflation and professional forecast dynamics: An evaluation of stickiness, persistence, and volatility By Elmar Mertens; James M. Nason
  2. A unit root test based on smooth transitions and nonlinear adjustment By Hepsag, Aycan
  4. Nonlinear models in macroeconometrics By Timo Teräsvirta
  5. Discovering pervasive and non-pervasive common cycles By Espasa Terrades, Antoni; Carlomagno Real, Guillermo
  6. Uncertainty Through the Lenses of A Mixed-Frequency Bayesian Panel Markov Switching Model By Casarin, Roberto; Foroni, Claudia; Marcellino, Massimiliano; Ravazzolo, Francesco
  7. Inference for VARs Identified with Sign Restrictions By Eleonora Granziera; Hyungsik Roger Moon; Frank Schorfheide
  8. Forecasting with Dynamic Panel Data Models By Laura Liu; Hyungsik Roger Moon; Frank Schorfheide
  9. Asymptotic Theory for Estimating the Persistent Parameter in the Fractional Vasicek Model By Xiao, Weilin; Yu, Jun
  10. Model Selection for Explosive Models By Tao, Yubo; Yu, Jun
  11. Autoregressive Spectral Averaging Estimator By Chu-An Liu; Biing-Shen Kuo; Wen-Jen Tsay

  1. By: Elmar Mertens; James M. Nason
    Abstract: This paper studies the joint dynamics of real time U.S. inflation and the mean inflation predictions of the Survey of Professional Forecasters (SPF) on a 1968Q4 to 2017Q2 sample. The joint data generating process (DGP) is an unobserved components (UC) model of inflation and a sticky information (SI) prediction mechanism for SPF inflation predictions. We add drifting gap inflation persistence to a UC model that already has stochastic volatility (SV) afflicting trend and gap inflation. Another innovation puts a time-varying frequency of inflation forecast updating into the SI-prediction mechanism. The joint DGP is a nonlinear state space model (SSM). We estimate the SSM using Bayesian tools grounded in a Rao-Blackwellized auxiliary particle filter, particle learning, and a particle smoother. The estimates show (i) longer horizon average SPF inflation predictions inform estimates of trend inflation, (ii) gap inflation persistence is pro-cyclical, and SI inflation updating is frequent before the Volcker disinflation, and (iii) subsequently, trend inflation and its SV fall, gap inflation persistence turns counter-cyclical, and SI inflation updating becomes infrequent.
    Keywords: Inflation, unobserved components, professional forecasts, sticky information, stochastic volatility, time-varying parameters, Bayesian, particle filter
    JEL: E31 C11 C32
    Date: 2017–09
  2. By: Hepsag, Aycan
    Abstract: In this paper, we develop a new unit root testing procedure which considers jointly for structural breaks and nonlinear adjustment. The structural breaks are modeled by means of a logistic smooth transition function and nonlinear adjustment is modeled by means of an ESTAR model. The empirical size of test is quite close to the nominal one and in terms of power, the new unit root test is generally superior to the alternative test.
    Keywords: Smooth Transition, nonlinearity, unit root, ESTAR
    JEL: C12 C22
    Date: 2017–10–05
  3. By: Ramazan Gencay (Simon Fraser University); Ege Yazgan (Istanbul Bilgi University)
    Abstract: When data exhibit high volatility and jumps, which are common features in most high frequency financial time series, forecasting becomes even more challenging. Using high frequency exchange rate data, we show that wavelets, which are robust to high volatility and jumps, are useful forecasters in high frequency settings when high volatility is a dominant feature that affects estimation zones, forecasting zones or both. The results indicate that decomposing the time series into homogeneous components that can then be used in time series forecast models is critical. Different components become more useful than others for different data features associated with a volatility regime. We cover a wide range of linear and nonlinear time series models for forecasting high frequency exchange rate return series. Our results indicate that when data display nonstandard features with high volatility, nonlinear models outperform linear alternatives. However, when data are in low volatility ranges for both estimations and forecasts, simple linear autoregressive models prevail, although considerable denoising of the data via wavelets is required.
    Keywords: Wavelets; Forecasting; High Frequency Data; Nonlinear Models; Maximum Overlap; Discrete Wavelet Transformation
    JEL: C12 C22
    Date: 2017–09
  4. By: Timo Teräsvirta (Aarhus University and CREATES, C.A.S.E., Humboldt-Universität zu Berlin)
    Abstract: This article contains a short review of nonlinear models that are applied to modelling macroeconomic time series. Brief descriptions of relevant models, both univariate, dynamic single-equation, and vector autoregressive ones are presented. Their application is illuminated by a number of selected examples.
    Keywords: Markov-switching model, nonlinear time series, random coefficient model, smooth transition model, threshold autoregressive model, vector autoregressive model
    JEL: C32 C51 E00
    Date: 2909
  5. By: Espasa Terrades, Antoni; Carlomagno Real, Guillermo
    Abstract: The objective of this paper is to propose a strategy to exploit short-run commonalities in the sectoral components of macroeconomic variables to obtain better models and more accurate forecasts of the aggregate and of the components. Our main contribution concerns cases in which the number of components is large, so that traditional multivariate approaches are not feasible. We show analytically and by Monte Carlo methods that subsets of components in which all the elements share a single common cycle can be discovered by pairwise methods. As the procedure does not rely on any kind of cross-sectional averaging strategy: it does not need to assume pervasiveness, it can deal with highly correlated idiosyncratic components and it does not need to assume that the size of the subsets goes to infinity. Nonetheless, the procedure works both with fixed N and T going to infinity, and with T and N both going to infinity.
    Keywords: Pairwise tests; Disaggregation; Factor Models; Common features
    JEL: C53 C32 C22 C01
    Date: 2017–09–01
  6. By: Casarin, Roberto; Foroni, Claudia; Marcellino, Massimiliano; Ravazzolo, Francesco
    Abstract: We propose a Bayesian panel model for mixed frequency data, where parameters can change over time according to a Markov process. Our model allows for both structural instability and random effects. To estimate the model, we develop a Markov Chain Monte Carlo algorithm for sampling from the joint posterior distribution of the model parameters, and we test its properties in simulation experiments. We use the model to study the effects of macroeconomic uncertainty and financiall uncertainty on a set of variables in a multi-country context including the US, several European countries and Japan. Wefind that for most of the variables financial uncertainty dominates macroeconomic uncertainty. Furthermore, we show that the effects of uncertainty differ whether the economy is in a contraction regime or in an expansion regime.
    Keywords: Bayesian inference; dynamic panel model; Markov switching; MCMC; mixed-frequency
    JEL: C13 C14 C51 C53
    Date: 2017–09
  7. By: Eleonora Granziera; Hyungsik Roger Moon; Frank Schorfheide
    Abstract: There is a fast growing literature that set-identifies structural vector autoregressions (SVARs) by imposing sign restrictions on the responses of a subset of the endogenous variables to a particular structural shock (sign-restricted SVARs). Most methods that have been used to construct pointwise coverage bands for impulse responses of sign-restricted SVARs are justified only from a Bayesian perspective. This paper demonstrates how to formulate the inference problem for sign-restricted SVARs within a moment-inequality framework. In particular, it develops methods of constructing confidence bands for impulse response functions of sign-restricted SVARs that are valid from a frequentist perspective. The paper also provides a comparison of frequentist and Bayesian coverage bands in the context of an empirical application - the former can be substantially wider than the latter.
    Date: 2017–09
  8. By: Laura Liu; Hyungsik Roger Moon; Frank Schorfheide
    Abstract: This paper considers the problem of forecasting a collection of short time series using cross sectional information in panel data. We construct point predictors using Tweedie's formula for the posterior mean of heterogeneous coefficients under a correlated random effects distribution. This formula utilizes cross-sectional information to transform the unit-specific (quasi) maximum likelihood estimator into an approximation of the posterior mean under a prior distribution that equals the population distribution of the random coefficients. We show that the risk of a predictor based on a non-parametric estimate of the Tweedie correction is asymptotically equivalent to the risk of a predictor that treats the correlated-random-effects distribution as known (ratio-optimality). Our empirical Bayes predictor performs well compared to various competitors in a Monte Carlo study. In an empirical application we use the predictor to forecast revenues for a large panel of bank holding companies and compare forecasts that condition on actual and severely adverse macroeconomic conditions.
    Date: 2017–09
  9. By: Xiao, Weilin (Zhejiang University); Yu, Jun (School of Economics, Singapore Management University)
    Abstract: This paper develops the asymptotic theory for the least squares (LS) estimator of the persistent parameter in the fractional Vasicek model when a continuous record of observations is available. The fractional Vasicek model is assumed to be driven by the fractional Brownian motion with a known Hurst parameter greater than or equal to one half. It is shown that the asymptotic properties depend on the sign of the persistent parameter, corresponding to the stationary case, the explosive case and the null recurrent case. The strong consistency and the asymptotic distribution are obtained in all three cases.
    Keywords: Least squares estimation; Fractional Vasicek model; Stationary process; Explosive process; Consistency; Asymptotic distribution
    JEL: C15 C22 C32
    Date: 2017–09–25
  10. By: Tao, Yubo (Singapore Management University); Yu, Jun (Singapore Management University)
    Abstract: This paper examines the limit properties of information criteria for distinguishing between the unit root model and the various kinds of explosive models. The information criteria include AIC, BIC, HQIC. The explosive models include the local-to-unit-root model, the mildly explosive model and the regular explosive model. Initial conditions with different order of magnitude are considered. Both the OLS estimator and the indirect inference estimator are studied. It is found that BIC and HQIC, but not AIC, consistently select the unit root model when data come from the unit root model. When data come from the local-to-unit-root model, both BIC and HQIC select the wrong model with probability approaching 1 while AIC has a positive probability of selecting the right model in the limit. When data come from the regular explosive model or from the mildly explosive model in the form of 1+n^{\alpha}/n with \alpha \in (0; 1), all three information criteria consistently select the true model. Indirect inference estimation can increase or decrease the probability for information criteria to select the right model asymptotically relative to OLS, depending on the information criteria and the true model. Simulation results confirm our asymptotic results in finite sample.
    Keywords: Model Selection; Information Criteria; Local-to-unit-root Model; Mildly Explosive Model; Unit Root Model; Indirect Inference.
    Date: 2016–03–29
  11. By: Chu-An Liu (Institute of Economics, Academia Sinica, Taipei, Taiwan); Biing-Shen Kuo (Department of International Business, National Chengchi University); Wen-Jen Tsay (Institute of Economics, Academia Sinica, Taipei, Taiwan)
    Abstract: This paper considers model averaging in spectral density estimation. We construct the spectral density function by averaging the autoregressive coefficients from all potential autoregressive models and investigate the autoregressive spectral averaging estimator using weights that minimize the Mallows and jackknife criteria. We extend the consistency of the autoregressive spectral estimator in Berk (1974) to the autoregressive spectral averaging estimator under a condition that imposes a restriction on the relationship between the model weights and autoregressive coefficients. Simulation studies show that the autoregressive spectral averaging estimator compares favorably with the AIC and BIC model selection estimators, and the bias of the averaging estimator approaches zero as the sample size increases.
    Keywords: Model averaging, Model selection, Spectral density estimator
    Date: 2017–09

This nep-ets issue is ©2017 by Yong Yin. 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.