nep-ecm New Economics Papers
on Econometrics
Issue of 2017‒05‒28
ten papers chosen by
Sune Karlsson
Örebro universitet

  1. An Efficient Bayesian Approach to Multiple Structural Change in Multivariate Time Series By Maheu, John M; Song, Yong
  2. Inference in Nonparametric Series Estimation with Data-Dependent Undersmoothing By Byunghoon Kang
  3. Bayesian Assessment of Lorenz and Stochastic Dominance By David Lander; David Gunawan; William Griffiths; Duangkamon Chotikapanich
  4. Alternative Graphical Representations of the Confidence Intervals for the Structural Coefficient from Exactly Identified Two-Stage Least Squares. By Joe Hirschberg; Jenny Lye
  5. A Robust Test of Exogeneity Based on Quantile Regressions By Tae-Hwan Kim; Christophe Muller
  6. When Multiple Objectives Meet Multiple Instruments: Identifying Simultaneous Monetary Shocks By Daniel Ordoñez-Callamand; Juan D. Hernandez-Leal; Mauricio Villamizar-Villegas
  7. Revealed Price Preference: Theory and Stochastic Testing By Rahul Deb; Yuichi Kitamura; John K.-H. Quah; Jorg Stoye
  8. Estimating non-stationary common factors : Implications for risk sharing By Ruiz Ortega, Esther; Poncela, Pilar; Corona, Francisco
  9. ASYMPTOTIC MULTIVARIATE EXPECTILES By Véronique Maume-Deschamps; Didier Rullière; Khalil Said
  10. Origins of Spurious Long Memory By Leschinski, Christian; Sibbertsen, Philipp

  1. By: Maheu, John M; Song, Yong
    Abstract: This paper provides a feasible approach to estimation and forecasting of multiple structural breaks for vector autoregressions and other multivariate models. Due to conjugate prior assumptions we obtain a very efficient sampler for the regime allocation variable. A new hierarchical prior is introduced to allow for learning over different structural breaks. The model is extended to independent breaks in regression coefficients and the volatility parameters.Two empirical applications show the improvements the model has over benchmarks. In a macro application with 7 variables we empirically demonstrate the benefits from moving from a multivariate structural break model to a set of univariate structural break models to account for heterogeneous break patterns across data series.
    Keywords: multivariate hierarchical prior, change point, forecasting
    JEL: C1 C11 C32 C53 E32
    Date: 2017–05
  2. By: Byunghoon Kang
    Abstract: Existing asymptotic theory for inference in nonparametric series estimation typically imposes an undersmoothing condition that the number of series terms is sufficiently large to make bias asymptotically negligible. However, there is no formally justified data-dependent method for this in practice. This paper constructs inference methods for nonparametric series regression models and introduces tests based on the infimum of t-statistics over different series terms. First, I provide an empirical process theory for the t-statistics indexed by the number of series terms. Using this result, I show that test based on the infimum of the t-statistics and its asymptotic critical value controls asymptotic size with undersmoothing condition. Using this test, we can construct a valid confidence interval (CI) by test statistic inversion that has correct asymptotic coverage probability. Allowing asymptotic bias without the undersmoothing condition, I show that CI based on the infimum of the t-statistics bounds coverage distortions. In an illustrative example, nonparametric estimation of wage elasticity of the expected labor supply from Blomquist and Newey (2002), proposed CI is close to or tighter than those based on the standard CI with the possible ad hoc choice of series terms.
    Keywords: Nonparametric series regression, Pointwise confidence interval, Smoothing parameter choice, Specification search, Undersmoothing
    JEL: C12 C14
    Date: 2017
  3. By: David Lander (Pennsylvania State University); David Gunawan (University of New South Wales); William Griffiths (Department of Economics, University of Melbourne); Duangkamon Chotikapanich (Monash University)
    Abstract: Because of their applicability for ordering distributions within general classes of utility and social welfare functions, sampling theory tests for stochastic and Lorenz dominance have attracted considerable attention in the literature. We contribute to this literature by proposing a Bayesian approach for assessing Lorenz and stochastic dominance. For two income distributions, say X and Y, estimated via Markov chain Monte Carlo (MCMC), we compute posterior probabilities for (i) X dominates Y, (ii) Y dominates X, and (iii) neither Y nor X is dominant by counting the proportions of MCMC draws that satisfy the constraints implied by each of the alternatives. We apply the proposed approach to samples of Indonesian income distributions for 1999, 2002, 2005 and 2008. To ensure flexible modelling of the distributions, mixtures of gamma densities are fitted for each of the years. We introduce probability curves that depict the probability of dominance at each population proportion and which convey valuable information about dominance probabilities for restricted population proportions relevant when studying poverty orderings. The dominance probabilities are compared with p-values from some sampling theory tests; the probability curves are used to gain insights into seemingly contradictory outcomes
    Keywords: Dominance probabilities, poverty comparisons, MCMC, gamma mixture.
    JEL: C11 C12 D31 I32
    Date: 2017–03
  4. By: Joe Hirschberg (Department of Economics, University of Melbourne); Jenny Lye (Department of Economics, University of Melbourne)
    Abstract: In the case of the just identified model the exact distribution of the two-stage least squares (2SLS) estimator of the coefficient of the endogenous regressor is a ratio of two normally distributed random variables. Robert Basmann (1960, 1961, 1974) used Fieller’s 1932 result to derive the density function of the estimator. In this paper we employ a novel graphical exposition of Fieller’s subsequent 1954 technique to approximate the confidence interval for the ratio. This approach involves the construction of a constraint shape that provides an insight as to how the characteristics of the reduced form estimates influences the comparison of the Delta and the Fieller confidence intervals. In particular, the degree of endogeneity and the relevance of the instrument can be shown to have a direct influence on these shapes. An example application of this approach is then applied to consider two specifications of an exactly identified model.
    Keywords: Indirect Least Squares, Inverse Test, Fieller Method, Anderson and Rubin Test, Delta Method
    JEL: C12 C26 C36 C18
    Date: 2017–01
  5. By: Tae-Hwan Kim (School of Economics, Yonsei University - Yonsei University); Christophe Muller (GREQAM - Groupement de Recherche en Économie Quantitative d'Aix-Marseille - CNRS - Centre National de la Recherche Scientifique - ECM - Ecole Centrale de Marseille - AMU - Aix Marseille Université - EHESS - École des hautes études en sciences sociales)
    Abstract: In this paper, we propose a robust test of exogeneity. The test statistics is constructed from quantile regression estimators, which are robust to heavy tails of errors. We derive the asymptotic distribution of the test statistic under the null hypothesis of exogeneity at a given quantile. Then, the finite sample properties of the test are investigated through Monte Carlo simulations that exhibit not only good size and power properties, but also good robustness to outliers.
    Keywords: regression quantile,endogeneity,two-stage estimation,Hausman test
    Date: 2017–04
  6. By: Daniel Ordoñez-Callamand (Banco de la República de Colombia); Juan D. Hernandez-Leal (Banco de la República de Colombia); Mauricio Villamizar-Villegas (Banco de la República de Colombia)
    Abstract: Central banks generally target multiple objectives while having at least the same number of monetary instruments. However, some instruments can be inadvertently collinear, leading to indeterminacy and identification failures. Paradoxically, most empirical studies have shied away from this dependence. In this paper we propose a novel method of identifying simultaneous monetary shocks by introducing a Tobit model within a VAR. An advantage of our method is that it can be easily estimated using only least squares and a maximum likelihood function. Also, the impulse-response analysis can be carried out as in the traditional time-series setting and can be applied in a structural framework. Hence, we model a dual process consisting of a censored foreign exchange intervention policy along with a linear interest rate intervention policy. In simulation exercises we show that our method outperforms a benchmark case of estimating policy functions separately. In fact, as the covariance between shocks increases, so does the performance of our method. In our empirical approach, we estimate the policy covariance for the case of Colombia and Turkey and find significant differences when compared to the benchmark case. Classification JEL: C34, E52, E58
    Keywords: Simultaneous policies, Instrumental VAR; Tobit-VAR; Central bank intervention; Monetary trilemma
    Date: 2017–05
  7. By: Rahul Deb (University of Toronto); Yuichi Kitamura (Cowles Foundation, Yale University); John K.-H. Quah (Johns Hopkins University); Jorg Stoye (Bonn University)
    Abstract: We develop a model of demand where consumers trade-off the utility of consumption against the disutility of expenditure. This model is appropriate whenever a consumer’s demand over a strict subset of all available goods is being analyzed. Data sets consistent with this model are characterized by the absence of revealed preference cycles over prices. The model is readily generalized to the random utility setting, for which we develop nonparametric statistical tests. Our application on national household consumption data provides support for the model.
    Date: 2017–05
  8. By: Ruiz Ortega, Esther; Poncela, Pilar; Corona, Francisco
    Abstract: In this paper, we analyze and compare the finite sample properties of alternative factor extraction procedures in the context of non-stationary Dynamic Factor Models (DFMs). On top of considering procedures already available in the literature, we extend the hybrid method based on the combination of principal components and Kalman filter and smoothing algorithms to non-stationary models. We show that, unless the idiosyncratic noise is non-stationary, procedures based on extracting the factors using the nonstationary original series work better than those based on differenced variables. The results are illustrated in an empirical application fitting non-stationary DFM to aggregate GDP and consumption of the set of 21 OECD industrialized countries. The goal is to check international risk sharing is a short or long-run issue.
    Keywords: Risk sharing; Resilience; Principal components; Kalman filter; Non-stationary Dynamic Factor Models; Long-run/Short-run estimation; Consumption smoothing
    Date: 2017–05
  9. By: Véronique Maume-Deschamps (ICJ - Institut Camille Jordan [Villeurbanne] - ECL - École Centrale de Lyon - UCBL - Université Claude Bernard Lyon 1 - UJM - Université Jean Monnet [Saint-Etienne] - INSA - Institut National des Sciences Appliquées - CNRS - Centre National de la Recherche Scientifique); Didier Rullière (SAF - Laboratoire de Sciences Actuarielle et Financière - UCBL - Université Claude Bernard Lyon 1); Khalil Said (Ecole d'Actuariat - Université Laval)
    Abstract: In [16], a new family of vector-valued risk measures called multivariate expectiles is introduced. In this paper, we focus on the asymptotic behavior of these measures in a multivariate regular variations context. For models with equivalent tails, we propose an estimator of these multivariate asymptotic expectiles, in the Fréchet attraction domain case, with asymptotic independence, or in the comonotonic case.
    Keywords: Risk measures, multivariate expectiles, regular variations, extreme values, tail dependence functions
    Date: 2017–04–18
  10. By: Leschinski, Christian; Sibbertsen, Philipp
    Abstract: We consider a large class of structural change processes that generate spurious long memory. Among others, this class encompasses structural breaks as well as random level shift processes and smooth trends. The properties of these processes are studied based on a simple representation of their discrete Fourier transform. We find, that under very general conditions all of the models nested in this class generate poles in the periodogram at the zero frequency. These are of order $O(T)$, instead of the usual $O(T^2d)$ for long memory processes and $O(T^2)$ for a random walk. This order arises whenever both the mean changes and sample fractions at which they occur are non-degenerate, asymptotically.
    Keywords: Long Memory; Spurious Long Memory; Structural Change
    JEL: C18 C32
    Date: 2017–05

This nep-ecm issue is ©2017 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.