nep-ecm New Economics Papers
on Econometrics
Issue of 2022‒04‒25
nineteen papers chosen by
Sune Karlsson
Örebro universitet

  1. Inference on Multiplicative Component GARCH without any Small-Order Moment By Christian Francq; Baye Matar Kandji; Jean-Michel Zakoian
  2. Estimation for double-nonlinear cointegration By Lin, Yingqian; Tu, Yundong; Yao, Qiwei
  3. Fast estimation of Kendall's Tau and conditional Kendall's Tau matrices under structural assumptions By Rutger van der Spek; Alexis Derumigny
  4. Identification and Estimation of Categorical Random Coeficient Models By Gao, Z.; Pesaran, M. H.
  5. Dynamic Identification Using System Projections and Instrumental Variables By Daniel J. Lewis; Karel Mertens
  6. Bivariate Distribution Regression with Application to Insurance Data By Yunyun Wang; Tatsushi Oka; Dan Zhu
  7. Multi–Level Panel Data Models: Estimation and Empirical Analysis By Guohua Feng; Jiti Gao; Bin Peng
  8. Sparse Synthetic Controls By Jaume Vives-i-Bastida
  9. Bounds for Bias-Adjusted Treatment Effect in Linear Econometric Models By Deepankar Basu
  10. Bivariate mixed Poisson regression models with varying dispersion By Tzougas, George; di Cerchiara, Alice Pignatelli
  11. Using Digitized Newspapers to Refine Historical Measures: The Case of the Boll Weevil By Andreas Ferrara; Joung Yeob Ha; Randall Walsh
  12. On Testing for Bubbles During Hyperinflations By Rubens Morita; Zacharias Psaradakis; Martín Sola; Patricio Yunis
  13. An Augmented Steady-State Kalman Filter to Evaluate the Likelihood of Linear and Time-Invariant State-Space Models By Johannes Huber
  14. Causality and Econometrics By James J. Heckman; Rodrigo Pinto
  15. A Modern Gauss-Markov Theorem? Really? By Pötscher, Benedikt M.; Preinerstorfer, David
  16. High Dimensional Factor Models with an Application to Mutual Fund Characteristics By Martin Lettau
  17. Comment on Andrews (1991) “Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimation” By Alessandro Casini
  18. Discrete choice analysis of health worker job preferences in Ethiopia: separating attribute non-attendance from taste heterogeneity By Arora, Nikita; Quaife, Matthew; Hanson, Kara; Lagarde, Mylène; Woldesenbet, Dorka; Seifu, Abiy; Crastes dit Sourd, Romain
  19. Seasonal adjustment of daily data with CAMPLET By Barend Abeln; Jan P.A.M. Jacobs; Machiel Mulder

  1. By: Christian Francq (CREST-ENSAE and University of Lille); Baye Matar Kandji (CREST-ENSAE); Jean-Michel Zakoian (University of Lille and CREST-ENSAE)
    Abstract: In multiplicative component GARCH models, the volatility is decomposed into the product of two factors which often received interpretations in terms of "short run" (high frequency) and "long run" (low frequency) components. While two-component volatility models are widely used in applied works, some of their theoretical properties remain unexplored. We show that the strictly stationary solutions of such models do not admit any small-order nite moment, contrary to classical GARCH. It is shown that the strong consistency and the asymptotic normality of the Quasi-Maximum Likelihood estimator hold despite the absence of moments. Tests for the presence of a long-run volatility relying on the asymptotic theory and a bootstrap procedure are proposed. Our results are illustrated via Monte Carlo experiments and real nancial data.
    Keywords: GARCH-MIDAS, Moments existence, QMLE, Residual Bootstrap, Tests on boundary parameters.
    JEL: C12 C13 C22 C58
    Date: 2022–03–18
  2. By: Lin, Yingqian; Tu, Yundong; Yao, Qiwei
    Abstract: In recent years statistical inference for nonlinear cointegration has attracted attention from both academics and practitioners. This paper proposes a new type of cointegration in the sense that two univariate time series yt and xt are cointegrated via two (unknown) smooth nonlinear transformations, further generalizing the notion of cointegration initially revealed by Box and Tiao (1977), and more systematically studied by Engle and Granger (1987). More precisely, it holds that G(yt,β0)=g(xt)+ut, where G(⋅,β0) is strictly increasing and known up to an unknown parameter β0, g(⋅) is unknown and smooth, xt is I(1), and ut is the stationary disturbance. This setting nests the nonlinear cointegration model of Wang and Phillips (2009b) as a special case with G(y,β0)=y. It extends the model of Linton et al. (2008) to the cases with a unit-root nonstationary regressor. Sieve approximations to the smooth nonparametric function g are applied, leading to an extremum estimator for β and a plugging-in estimator for g(⋅). Asymptotic properties of the estimators are established, revealing that both the convergence rates and the limiting distributions depend intimately on the properties of the two nonlinear transformation functions. Simulation studies demonstrate that the estimators perform well even with small samples. A real data example on the environmental Kuznets curve portraying the nonlinear impact of per-capita GDP on air-pollution illustrates the practical relevance of the proposed double-nonlinear cointegration.
    Keywords: Box–Cox transformation; nonlinear cointegration; semiparametrics; sieve method; transformation models
    JEL: J1 C1
    Date: 2020–05–01
  3. By: Rutger van der Spek; Alexis Derumigny
    Abstract: Kendall's tau and conditional Kendall's tau matrices are multivariate (conditional) dependence measures between the components of a random vector. For large dimensions, available estimators are computationally expensive and can be improved by averaging. Under structural assumptions on the underlying Kendall's tau and conditional Kendall's tau matrices, we introduce new estimators that have a significantly reduced computational cost while keeping a similar error level. In the unconditional setting we assume that, up to reordering, the underlying Kendall's tau matrix is block-structured with constant values in each of the off-diagonal blocks. Consequences on the underlying correlation matrix are then discussed. The estimators take advantage of this block structure by averaging over (part of) the pairwise estimates in each of the off-diagonal blocks. Derived explicit variance expressions show their improved efficiency. In the conditional setting, the conditional Kendall's tau matrix is assumed to have a constant block structure, independently of the conditioning variable. Conditional Kendall's tau matrix estimators are constructed similarly as in the unconditional case by averaging over (part of) the pairwise conditional Kendall's tau estimators. We establish their joint asymptotic normality, and show that the asymptotic variance is reduced compared to the naive estimators. Then, we perform a simulation study which displays the improved performance of both the unconditional and conditional estimators. Finally, the estimators are used for estimating the value at risk of a large stock portfolio; backtesting illustrates the obtained improvements compared to the previous estimators.
    Date: 2022–04
  4. By: Gao, Z.; Pesaran, M. H.
    Abstract: This paper proposes a linear categorical random coefficient model, in which the random coefficients follow parametric categorical distributions. The distributional parameters are identified based on a linear recurrence structure of moments of the random coefficients. A Generalized Method of Moments estimator is proposed, and its finite sample properties are examined using Monte Carlo simulations. The utility of the proposed method is illustrated by estimating the distribution of returns to education in the U.S. by gender and educational levels. We find that rising heterogeneity between educational groups is mainly due to the increasing returns to education for those with postsecondary education, whereas within group heterogeneity has been rising mostly in the case of individuals with high school or less education.
    Keywords: Random coefficient models, categorical distribution, return to education
    JEL: C01 C21 C13 C46 J30
    Date: 2022–04–14
  5. By: Daniel J. Lewis; Karel Mertens
    Abstract: We propose System Projections with Instrumental Variables (SP-IV) to estimate dynamic structural relationships. SP-IV replaces lag sequences of instruments in traditional IV with lead sequences of endogenous variables. SP-IV allows the inclusion of controls to weaken exogeneity requirements, can be more efficient than IV with lags, and allows identification over many time horizons without creating many-weak-instruments problems. SP-IV also enables the estimation of structural relationships across impulse responses obtained from local projections or vector autoregressions. We provide a bias-based test for instrument strength, and inference procedures under strong and weak identification. SP-IV outperforms competing estimators of the Phillips Curve parameters in simulations. We estimate the Phillips Curve implied by the main business cycle shock of Angeletos et al. (2020), and find evidence for forward-looking behavior. The data is consistent with weak but also relatively strong cyclical connections between inflation and unemployment.
    Keywords: Structural Equations; Instrumental Variables; Impulse Responses; Robust Inferences; Phillips Curve; Inflation Dynamics
    JEL: E3 C32 C36
    Date: 2022–03–30
  6. By: Yunyun Wang; Tatsushi Oka; Dan Zhu
    Abstract: This article introduces an estimation method for the conditional joint distribution of bivariate outcomes, based on the distribution regression approach and the factorization method. The proposed method can apply for discrete, continuous or mixed distribution outcomes. It is semiparametric in that both marginal and joint distributions are left unspecified, conditional on covariates. Unlike the existing parametric approaches, our method is simple yet flexible to encapsulate distributional dependence structures of bivariate outcomes and covariates. Various simulation results confirm that our method can perform similarly or better in finite samples compared to the alternative methods. In an application to the study of a motor third-part liability insurance portfolio, the proposed method effectively captures key distributional features in the data, especially the value at risks conditional on covariates. This result suggests that this semiparametric approach can serve as an alternative in insurance risk management.
    Date: 2022–03
  7. By: Guohua Feng; Jiti Gao; Bin Peng
    Abstract: Despite its paramount importance in the empirical growth literature, productivity convergence analysis has three issues that have yet to be addressed: (1) the hierarchical structure of industry-level datasets has little been fully explored; (2) industry-level technology heterogeneity has largely been ignored; and (3) crosssectional dependence has rarely been allowed for. This paper aims to address these three problems within a hierarchical panel data framework. We establish asymptotic properties for the proposed estimator, and apply the framework to a dataset of 23 manufacturing industries from a wide range of countries over the period 1963-2018. Our results show that both the manufacturing industry as a whole and individual manufacturing industries at the ISIC two-digit level exhibit strong conditional convergence in labour productivity, but not unconditional convergence. In addition, our results show that both global and industry-specific shocks are important in explaining the convergence behaviours of the manufacturing industries.
    Keywords: Convergence in manufacturing, cross-sectional dependence, growth regression, hierarchical model
    JEL: L60 O10 C23
    Date: 2022
  8. By: Jaume Vives-i-Bastida
    Abstract: This paper introduces a new penalized synthetic control method for policy evaluation. The proposed sparse synthetic control penalizes the number of predictors used in generating the counterfactual to improve pre-treatment fit and select the most important predictors. To motivate the method theoretically I derive, in a linear factor model framework, a model selection consistency result and a mean squared error convergence rate result. Through a simulation study, I then show that the sparse synthetic control achieves lower bias and has better post-treatment fit than the unpenalized synthetic control. Finally, I apply the method to study the effects of the passage of Proposition 99 in California in a setting with a large number of predictors.
    Date: 2022–03
  9. By: Deepankar Basu
    Abstract: In linear econometric models with proportional selection on unobservables, omitted variable bias in estimated treatment effects are real roots of a cubic equation involving estimated parameters from a short and intermediate regression. The roots of the cubic are functions of $\delta$, the degree of selection on unobservables, and $R_{max}$, the R-squared in a hypothetical long regression that includes the unobservable confounder and all observable controls. In this paper I propose and implement a novel algorithm to compute roots of the cubic equation over relevant regions of the $\delta$-$R_{max}$ plane and use the roots to construct bounding sets for the true treatment effect. The algorithm is based on two well-known mathematical results: (a) the discriminant of the cubic equation can be used to demarcate regions of unique real roots from regions of three real roots, and (b) a small change in the coefficients of a polynomial equation will lead to small change in its roots because the latter are continuous functions of the former. I illustrate my method by applying it to the analysis of maternal behavior on child outcomes.
    Date: 2022–03
  10. By: Tzougas, George; di Cerchiara, Alice Pignatelli
    Abstract: The main purpose of this article is to present a new class of bivariate mixed Poisson regression models with varying dispersion that offers sufficient flexibility for accommodating overdispersion and accounting for the positive correlation between the number of claims from third-party liability bodily injury and property damage. Maximum likelihood estimation for this family of models is achieved through an expectation-maximization algorithm that is shown to have a satisfactory performance when three members of this family, namely, the bivariate negative binomial, bivariate Poisson–inverse Gaussian, and bivariate Poisson–Lognormal distributions with regression specifications on every parameter are fitted on two-dimensional motor insurance data from a European motor insurer. The a posteriori, or bonus-malus, premium rates that are determined by these models are calculated via the expected value and variance principles and are compared to those based only on the a posteriori criteria. Finally, we present an extension of the proposed approach with varying dispersion by developing a bivariate Normal copula-based mixed Poisson regression model with varying dispersion and dependence parameters. This approach allows us to consider the influence of individual and coverage-specific risk factors on the mean, dispersion, and copula parameters when modeling different types of claims from different types of coverage. For expository purposes, the Normal copula paired with negative binomial distributions for marginals and regressors on the mean, dispersion, and copula parameters is fitted on a simulated dataset via maximum likelihood.
    JEL: C1
    Date: 2021–10–30
  11. By: Andreas Ferrara; Joung Yeob Ha; Randall Walsh
    Abstract: This paper shows how to remove attenuation bias in regression analyses due to measurement error in historical data for a given variable of interest by using a secondary measure which can be easily generated from digitized newspapers. We provide three methods for using this secondary variable to deal with non-classical measurement error in a binary treatment: set identification, bias reduction via sample restriction, and a parametric bias correction. We demonstrate the usefulness of our methods by replicating two recent studies on the effect of the boll weevil. Relative to the initial analysis, our results yield markedly larger coefficient estimates.
    JEL: N01
    Date: 2022–02
  12. By: Rubens Morita; Zacharias Psaradakis; Martín Sola; Patricio Yunis
    Abstract: We consider testing for the presence of rational bubbles during hyperinflations via an analysis of the non-stationarity properties of relevant observable time series. The testing procedure is based on a Markov-regime switching model with independent stochastic changes in its intercept, error variance, and autoregressive coefficients. This model formulation allow us to disentangle fundamentals-driven changes in the drift, bubble-driven explosiveness, and volatility changes that may be fundamentals-driven and/or bubble-driven. The testing strategy is illustrated by applying it to data from hyperinflations in Argentina, Brazil, Germany, and Poland.
    Keywords: Bubbles; Explosiveness; Markov-switching autoregressive model; Unit-root test.
    JEL: C72 D44 D82
  13. By: Johannes Huber (University of Augsburg, Department of Economics)
    Abstract: We propose a modified version of the augmented Kalman filter (AKF) to evaluate the likelihood of linear and time-invariant state-space models (SSMs). Unlike the regular AKF, this augmented steady-state Kalman filter (ASKF), as we call it, is based on a steady-state Kalman filter (SKF). We show that to apply the ASKF, it is sufficient that the SSM at hand is stationary. We find that the ASKF can significantly reduce the computational burden to evaluate the likelihood of medium- to large-scale SSMs, making it particularly useful to estimate dynamic stochastic general equilibrium (DSGE) models and dynamic factor models. Tests using a medium-scale DSGE model, namely the 2007 version of the Smets and Wouters model, show that the ASKF is up to five times faster than the regular Kalman filter (KF). Other competing algorithms, such as the Chandrasekhar recursion (CR) or a univariate treatment of multivariate observation vectors (UKF), are also outperformed by the ASKF in terms of computational efficiency.
    Keywords: kalman filter, dsge, bayesian estimation, maximum-likelihood estimation, computational techniques
    JEL: C18 C63 E20
    Date: 2022–04
  14. By: James J. Heckman; Rodrigo Pinto
    Abstract: This paper examines the econometric causal model for policy analysis developed by the seminal ideas of Ragnar Frisch and Trygve Haavelmo. We compare the econometric causal model with two popular causal frameworks: Neyman-Holland causal model and the do-calculus. The Neyman-Holland causal model is based on the language of potential outcomes and was largely developed by statisticians. The do-calculus, developed by Judea Pearl and co-authors, relies on Directed Acyclic Graphs (DAGs) and is a popular causal framework in computer science. We make the case that economists who uncritically use these approximating frameworks often discard the substantial benefits of the econometric causal model to the detriment of more informative economic policy analyses. We illustrate the versatility and capabilities of the econometric framework using causal models that are frequently studied by economists.
    JEL: C10 C18
    Date: 2022–02
  15. By: Pötscher, Benedikt M.; Preinerstorfer, David
    Abstract: We show that the theorems in Hansen (2021b) (Econometrica, forthcoming) are not new as they coincide with classical theorems like the good old Gauss-Markov or Aitken Theorem, respectively.
    Keywords: Gauss-Markov Theorem, Aitken Theorem, unbiased estimation
    JEL: C13 C20
    Date: 2022–02
  16. By: Martin Lettau
    Abstract: This paper considers extensions of 2-dimensional factor models to higher-dimension data that can be represented as tensors. I describe decompositions of tensors that generalize the standard matrix singular value decomposition and principal component analysis to higher dimensions. I estimate the model using a 3-dimensional data set consisting of 25 characteristics of 1,342 mutual funds observed over 34 quarters. The tensor factor models reduce the data dimensionality by 97% while capturing 93% of the variation of the data. I relate higher-dimensional tensor models to standard 2-dimensional models and show that the components of the model have clear economic interpretations.
    JEL: C38 G12
    Date: 2022–03
  17. By: Alessandro Casini (Università di Roma "Tor Vergata")
    Abstract: This comment includes a solution to a problem in Section 8 in Andrews (1991) and points out a method to generalize the mean-squared error (MSE) bounds appearing in Andrews (1988) and Andrews (1991)
    Date: 2022–04–02
  18. By: Arora, Nikita; Quaife, Matthew; Hanson, Kara; Lagarde, Mylène; Woldesenbet, Dorka; Seifu, Abiy; Crastes dit Sourd, Romain
    Abstract: When measuring preferences, discrete choice experiments (DCEs) typically assume that respondents consider all available information before making decisions. However, many respondents often only consider a subset of the choice characteristics, a heuristic called attribute non-attendance (ANA). Failure to account for ANA can bias DCE results, potentially leading to flawed policy recommendations. While conventional latent class logit models have most commonly been used to assess ANA in choices, these models are often not flexible enough to separate non-attendance from respondents’ low valuation of certain attributes, resulting in inflated rates of ANA. In this paper, we show that semi-parametric mixtures of latent class models can be used to disentangle successfully inferred non-attendance from respondent’s ‘weaker’ taste sensitivities for certain attributes. In a DCE on the job preferences of health workers in Ethiopia, we demonstrate that such models provide more reliable estimates of inferred non-attendance than the alternative methods currently used. Moreover, since we find statistically significant variation in the rates of ANA exhibited by different health worker cadres, we highlight the need for well-defined attributes in a DCE, to ensure that ANA does not result from a weak experimental design.
    Keywords: attribute non-attendance; Preference heterogeneity; discrete choice experiment; health workers; Grant 212771/Z/18/Z);; Gates Global Health Grant Number: OPP1149259
    JEL: C01 C35 D01 D80
    Date: 2022–02–17
  19. By: Barend Abeln; Jan P.A.M. Jacobs; Machiel Mulder
    Abstract: In the last decade large data sets have become available, both in terms of the number of time series and with higher frequencies (weekly, daily and even higher). All series may suffer from seasonality, which hides other important fluctuations. Therefore time series are typically seasonally adjusted. However, standard seasonal adjustment methods cannot handle series with higher than monthly frequencies. Recently, Abeln et al. (2019) presented CAMPLET, a new seasonal adjustment method, which does not produce revisions when new observations become available. The aim of this paper is to show the attractiveness of CAMPLET for seasonal adjustment of daily time series. We apply CAMPLET to daily data on the gas system in the Netherlands. To quote this document: Au cours de la dernière décennie, de vastes ensembles de données sont devenus disponibles, tant en termes de nombre de séries chronologiques que de fréquences plus élevées (hebdomadaires, quotidiennes et même supérieures). Toutes les séries peuvent souffrir d'une saisonnalité, qui masque d'autres fluctuations importantes. C'est pourquoi les séries temporelles sont généralement désaisonnalisées. Cependant, les méthodes standard de désaisonnalisation ne peuvent pas traiter les séries dont la fréquence est supérieure au mois. Récemment, Abeln et al. (2019) ont présenté CAMPLET, une nouvelle méthode de désaisonnalisation, qui ne produit pas de révisions lorsque de nouvelles observations sont disponibles. L'objectif de cet article est de montrer l'attrait de CAMPLET pour l'ajustement saisonnier des séries temporelles quotidiennes. Nous appliquons CAMPLET à des données quotidiennes sur le réseau de gaz aux Pays-Bas. Pour citer ce document:
    Keywords: daily data,seasonal adjustment,calendar effect,gas system,the Netherlands, données quotidiennes,ajustement saisonnier,effet de calendrier,système de gaz,les Pays-Bas.
    JEL: C22 Q47
    Date: 2022–04–04

This nep-ecm issue is ©2022 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.