nep-ets New Economics Papers
on Econometric Time Series
Issue of 2014‒08‒09
eight papers chosen by
Yong Yin
SUNY at Buffalo

  1. Multivariate Self-Exciting Threshold Autoregressive Models with eXogenous Input By Peter Martey Addo
  2. Bayesian estimation of realized stochastic volatility model by Hybrid Monte Carlo algorithm By Tetsuya Takaishi
  3. Contrasting Bayesian and Frequentist Approaches to Autoregressions: the Role of the Initial Condition By Marek Jarociński; Albert Marcet
  4. How good are out of sample forecasting Tests on DSGE models? By Minford, Patrick; Xu, Yongden; Zhou, Peng
  5. Spatial Effects in Dynamic Conditional Correlations By E. Otranto; M. Mucciardi; P. Bertuccelli
  6. Filtering and Prediction in Noncausal Processes By Christian Gouriéroux; Joann Jasiak
  7. Analyzing interrelated stochastic trend and seasonality on the example of energy trading data By Mák, Fruzsina
  8. Variance targeting estimation of multivariate GARCH models By Francq, Christian; Horvath, Lajos; Zakoian, Jean-Michel

  1. By: Peter Martey Addo
    Abstract: This study defines a multivariate Self--Exciting Threshold Autoregressive with eXogenous input (MSETARX) models and present an estimation procedure for the parameters. The conditions for stationarity of the nonlinear MSETARX models is provided. In particular, the efficiency of an adaptive parameter estimation algorithm and LSE (least squares estimate) algorithm for this class of models is then provided via simulations.
    Date: 2014–07
  2. By: Tetsuya Takaishi
    Abstract: The hybrid Monte Carlo algorithm (HMCA) is applied for Bayesian parameter estimation of the realized stochastic volatility (RSV) model. Using the 2nd order minimum norm integrator (2MNI) for the molecular dynamics (MD) simulation in the HMCA, we find that the 2MNI is more efficient than the conventional leapfrog integrator. We also find that the autocorrelation time of the volatility variables sampled by the HMCA is very short. Thus it is concluded that the HMCA with the 2MNI is an efficient algorithm for parameter estimations of the RSV model.
    Date: 2014–08
  3. By: Marek Jarociński; Albert Marcet
    Abstract: The frequentist and the Bayesian approach to the estimation of autoregressions are often contrasted. Under standard assumptions, when the ordinary least squares (OLS) estimate is close to 1, a frequentist adjusts it upwards to counter the small sample bias, while a Bayesian who uses a at prior considers the OLS estimate to be the best point estimate. This contrast is surprising because a at prior is often interpreted as the Bayesian approach that is closest to the frequentist approach. We point out that the standard way that inference has been compared is misleading because frequentists and Bayesians tend to use different models, in particular, a different distribution of the initial condition. The contrast between the frequentist and the Bayesian at prior estimation of the autoregression disappears once we make the same assumption about the initial condition in both approaches.
    Keywords: autoregression, initial condition, bayesian estimation, small sample distribution, bias correction
    JEL: C11 C22 C32
    Date: 2014–07
  4. By: Minford, Patrick (Cardiff Business School); Xu, Yongden; Zhou, Peng (Cardiff Business School)
    Abstract: Out-of-sample forecasting tests of DSGE models against time-series benchmarks such as an unrestricted VAR are increasingly used to check a) the specification b) the forecasting capacity of these models. We carry out a Monte Carlo experiment on a widely-used DSGE model to investigate the power of these tests. We find that in specification testing they have weak power relative to an in-sample indirect inference test; this implies that a DSGE model may be badly mis-specified and still improve forecasts from an unrestricted VAR. In testing forecasting capacity they also have quite weak power, particularly on the lefthand tail. By contrast a model that passes an indirect inference test of specification will almost definitely also improve on VAR forecasts.
    Keywords: Out of sample forecasts; DSGE; VAR; specification tests; indirect inference; forecast performance
    JEL: E10 E17
    Date: 2014–07
  5. By: E. Otranto; M. Mucciardi; P. Bertuccelli
    Abstract: The recent literature on time series has developed a lot of models for the analysis of the dynamic conditional correlation, involving the same variable observed in different locations; very often, in this framework, the consideration of the spatial interactions are omitted. We propose to extend a time-varying conditional correlation model (following an ARMA dynamics) to include the spatial effects, with a specification depending on the local spatial interactions. The spatial part is based on a fixed symmetric weight matrix, called Gaussian Kernel Matrix (GKM), but its effect will vary along the time depending on the degree of time correlation in a certain period. We show the theoretical aspects, with the support of simulation experiments, and apply this methodology to two space-time data sets, in a demographic and a financial framework respectively.
    Keywords: space-time correlation, time-varying correlation, weight matrix, gaussian kernel
    JEL: C13 C33 J13
    Date: 2014
  6. By: Christian Gouriéroux (CREST and University of Toronto); Joann Jasiak (York University)
    Abstract: This paper revisits the filtering and prediction in noncausal and mixed autoregressive processes and provides a simple alternative set of methods that are valid for processes with infinite variances. The prediction method provides complete predictive densities and prediction intervals at any finite horizon H, for univariate and multivariate processes. It is based on an unobserved component representation of noncausal processes. The filtering procedure for the unobserved components is provided along with a simple back-forecasting estimator for the parameters of noncausal and mixed models and a simulation algorithm for noncausal and mixed autoregressive processes. The approach is illustrated by simulations
    Keywords: Noncausal Process, Nonlinear Prediction, Filtering, Look-Ahead Estimator, Speculative Bubble, Technical Analysis
    JEL: C14 G32 G23
    Date: 2014–04
  7. By: Mák, Fruzsina
    Abstract: The correct modelling of long- and short-term seasonality is a very interesting issue. The choice between the deterministic and stochastic modelling of trend and seasonality and their implications are as relevant as the case of deterministic and stochastic trends itself. The study considers the special case when the stochastic trend and seasonality do not evolve independently and the usual differencing filters do not apply. The results are applied to the day-ahead (spot) trading data of some main European energy exchanges (power and natural gas).
    Keywords: unit root, seasonality, energy exchange
    JEL: C22 Q41
    Date: 2014
  8. By: Francq, Christian; Horvath, Lajos; Zakoian, Jean-Michel
    Abstract: We establish the strong consistency and the asymptotic normality of the variance-targeting estimator (VTE) of the parameters of the multivariate CCC-GARCH($p,q$) processes. This method alleviates the numerical difficulties encountered in the maximization of the quasi likelihood by using an estimator of the unconditional variance. It is shown that the distribution of the VTE can be consistently estimated by a simple residual bootstrap technique. We also use the VTE for testing the model adequacy. A test statistic in the spirit of the score test is constructed, and its asymptotic properties are derived under the null assumption that the model is well specified. An extension of the VT method to asymmetric CCC-GARCH models incorporating leverage effects is studied. Numerical illustrations are provided and an empirical application based on daily exchange rates is proposed.
    Keywords: Adequacy Test for CCC-GARCH models, Bootstrap, Leverage Effect, Quasi Maximum Likelihood Estimation, Variance Targeting Estimator
    JEL: C13 C22
    Date: 2014–08–06

This nep-ets issue is ©2014 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.