nep-ecm New Economics Papers
on Econometrics
Issue of 2016‒09‒04
seven papers chosen by
Sune Karlsson
Örebro universitet

  1. Choosing Prior Hyperparameters By Amir-Ahmadi, Pooyan; Matthes, Christian; Wang, Mu-Chun
  2. Accounting for Missing Values in Score-Driven Time-Varying Parameter Models By Andre Lucas; Anne Opschoor; Julia Schaumburg
  3. A Multivariate Asymmetric Long Memory Conditional Volatility Model with X, Regularity and Asymptotics By Manabu Asai; Michael McAleer
  4. Wage Decompositions Using Panel Data Sample Selection Correction By Oaxaca, Ronald L.; Choe, Chung
  5. Exclusion Bias in the Estimation of Peer Effects By Bet Caeyers; Marcel Fafchamps
  6. HEGY test under seasonal heterogeneity By Politis, Dimitris
  7. Determining the Cointegration Rank in Heteroskedastic VAR Models of Unknown Order By Cavaliere, Giuseppe; De Angelis, Luca; Rahbek, Anders; Taylor, A M Robert

  1. By: Amir-Ahmadi, Pooyan (Gothe University Frankfurt); Matthes, Christian (Federal Reserve Bank of Richmond); Wang, Mu-Chun (University of Hamburg)
    Abstract: Bayesian inference is common in models with many parameters, such as large VAR models, models with time-varying parameters, or large DSGE models. A common practice is to focus on prior distributions that themselves depend on relatively few hyperparameters. The choice of these hyperparameters is crucial because their influence is often sizeable for standard sample sizes. In this paper we treat the hyperparameters as part of a hierarchical model and propose a fast, tractable, easy-to-implement, and fully Bayesian approach to estimate those hyperparameters jointly with all other parameters in the model. In terms of applications, we show via Monte Carlo simulations that in time series models with time-varying parameters and stochastic volatility, our approach can drastically improve on using fixed hyperparameters previously proposed in the literature.
    Date: 2016–08–23
  2. By: Andre Lucas (VU University Amsterdam, the Netherlands); Anne Opschoor (VU University Amsterdam, the Netherlands); Julia Schaumburg (VU University Amsterdam, the Netherlands)
    Abstract: We show that two alternative perspectives on how to deal with missing data in the context of the score-driven time-varying parameter models of Creal, Koopman, Lucas (2013) and Harvey (2013) lead to precisely the same dynamic transition equations. As score-driven models encompass a wide variety of time-varying parameter models (including generalized autoregressive conditional volatility (GARCH) and duration (ACD) models), the results apply to a wide range of empirically relevant models as applied in economics and statistics.
    Keywords: generalized autoregressive score models; missing completely at random; Expectation-Maximization
    JEL: C52 C53
    Date: 2016–08–29
  3. By: Manabu Asai (Soka University, Japan); Michael McAleer (National Tsing Hua University Taiwan; Erasmus School of Economics Erasmus University Rotterdam, The Netherlands; Yokohama National University, Japan)
    Abstract: The paper derives a Multivariate Asymmetric Long Memory conditional volatility model with Exogenous Variables (X), or the MALMX model, with dynamic conditional correlations, appropriate regularity conditions, and associated asymptotic theory. This enables checking of internal consistency and allows valid statistical inferences to be drawn based on empirical estimation. The underlying vector random coefficient autoregressive process, which has well established regularity conditions and associated asymptotic properties, is discussed, and a simple explanation is given as to why only the diagonal BEKK model, and not the Hadamard, triangular or full BEKK models, has regularity conditions and asymptotic properties. Various special cases, including the diagonal BEKK model of Baba et al. (1985) and Engle and Kroner (1995), VARMA-GARCH model of Ling and McAleer (2003), and VARMA-AGARCH model of McAleer et al. (2009), are discussed. There does not seem to have been a derivation of a univariate conditional volatility model with exogenous variables (X) that has dynamic conditional correlations, appropriate regularity conditions, and associated asymptotic theory. Therefore, the derivation of a multivariate conditional volatility model with exogenous variables (X) that has regularity conditions and asymptotic theory would seem to be a significant extension of the existing literature.
    Keywords: Multivariate conditional volatility; Vector random coefficient autoregressive process; Asymmetry; Long memory; Exogenous variables; Dynamic conditional correlations; Regularity conditions; Asymptotic properties
    JEL: C22 C52 C58 G32
    Date: 2016–08–29
  4. By: Oaxaca, Ronald L. (University of Arizona); Choe, Chung (Hanyang University)
    Abstract: This paper analyzes wage decomposition methodology in the context of panel data sample selection embedded in a correlated random effects setting. Identification issues unique to panel data are examined for their implications for wage decompositions. As an empirical example, we apply our methodology to German Socio-Economic Panel (GSOEP) data with which we investigate gender wage differentials in the German Labor Market. Our results highlight the sensitivity of inferences about potential discrimination to how elements of the panel data selection model are assigned to explained and unexplained components.
    Keywords: decomposition, panel data, GSOEP, sample selection
    JEL: J31 J71 C00
    Date: 2016–08
  5. By: Bet Caeyers; Marcel Fafchamps
    Abstract: We formalize a noted [Guryan et al., 2009] but unexplored source of bias in peer effect estimation, arising because people cannot be their own peer. We derive, for linear-in-means models with non-overlapping peer groups, an exact formula of the bias in a test of random peer assignment. We demonstrate that, when estimating endogenous peer effects, the negative exclusion bias dominates the positive reflection bias when the true peer effect is small. We discuss conditions under which exclusion bias is aggravated by adding cluster fixed effects. By imposing restrictions on the error term, we show how to consistently estimate, without the need for instruments, all the structural parameters of an endogenous peer effect model with an arbitrary peer-group or network structure. We show that, under certain conditions, 2SLS do not suffer from exclusion bias. This may explain the counter-intuitive observation that OLS estimates of peer effects are often larger than their 2SLS counterpart.
    JEL: C31
    Date: 2016–08
  6. By: Politis, Dimitris
    Keywords: Physical Sciences and Mathematics
    Date: 2016–09–01
  7. By: Cavaliere, Giuseppe; De Angelis, Luca; Rahbek, Anders; Taylor, A M Robert
    Abstract: We investigate the asymptotic and finite sample properties of a number of methods for estimating the cointegration rank in integrated vector autoregressive systems of unknown autoregressive order driven by heteroskedastic shocks. We allow for both conditional and unconditional heteroskedasticity of a very general form. We establish the conditions required on the penalty functions such that standard information criterion-based methods, such as the Bayesian information criterion [BIC], when employed either sequentially or jointly, can be used to consistently estimate both the cointegration rank and the autoregressive lag order. In doing so we also correct errors which appear in the proofs provided for the consistency of information-based estimators in the homoskedastic case by Aznar and Salvador (2002). We also extend the corpus of available large sample theory for the conventional sequential approach of Johansen (1995) and the associated wild bootstrap implementation thereof of Cavaliere, Rahbek and Taylor (2014) to the case where the lag order is unknown. In particular, we show that these methods remain valid under heteroskedasticity and an unknown lag length provided the lag length is first chosen by a consistent method, again such as the BIC. The relative finite sample properties of the different methods discussed are investigated in a Monte Carlo simulation study. The two best performing methods in this study are a wild bootstrap implementation of the Johansen (1995) procedure implemented with BIC selection of the lag length and joint IC approach (cf. Phillips, 1996) which uses the BIC to jointly select the lag order and the cointegration rank.
    Keywords: Cointegration rank; Information criteria; Wild bootstrap; Trace statistic; Lag length; Heteroskedasticity
    Date: 2016–08

This nep-ecm issue is ©2016 by Sune Karlsson. 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.