nep-ecm New Economics Papers
on Econometrics
Issue of 2011‒08‒29
twelve papers chosen by
Sune Karlsson
Orebro University

  1. Bayes estimators of log-normal means with finite quadratic expected loss By Enrico Fabrizi; Carlo Trivisano
  2. Sharp bounds on causal effects under sample selection By Huber, Martin; Mellace, Giovanni
  3. Testing for co-jumps in high-frequency financial data: an approach based on first-high-low-last prices By Yin Liao; Heather M. Anderson
  4. Sensitivity analysis of efficiency rankings to distributional assumptions: applications to Japanese water utilities By Yane, Shinji; Berg, Sanford
  5. Nowcasting Irish GDP By D'Agostino, Antonello; McQuinn, Kieran; O'Brien, Derry
  6. Applying and interpreting model-based seasonal adjustment. The euro-area industrial production series By Agustín Maravall Herrero; Domingo Pérez Cañete
  7. Being Focused: When the Purpose of Inference Matters for Model Selection By Peter Behl; Holger Dette; Manuel Frondel; Harald Tauchmann
  8. The empirical content of models with multiple equilibria in economies with social interactions By Alberto Bisin; Andrea Moro; Giorgio Topa
  9. The Fixed-Effects Zero-Inflated Poisson Model with an Application to Health Care Utilization By Majo, M.C.; Soest, A.H.O. van
  10. Default, liquidity and crises: an econometric framework By Monfort, A.; Renne, J-P.
  11. Three New Empirical Tests of the Pollution Haven Hypothesis When Environmental Regulation is Endogenous By Millimet, Daniel L.; Roy, Jayjit
  12. A Review and Bibliography of Early Warning Models By Yucel, Eray

  1. By: Enrico Fabrizi (Univeristà di Bologna); Carlo Trivisano (Univeristà di Bologna)
    Abstract: The log-normal distribution is a popular model in biostatistics as in many other fields of statistics. Bayesian inference on the mean and median of the distribution is problematic because, for many popular choices of the prior for variance (on the log-scale) parameter, the posterior distribution has no finite moments, leading to Bayes estimators with infinite expected loss for the most common choices of the loss function. In this paper we propose a generalized inverse Gaussian prior for the variance parameter, that leads to a log-generalized hyperbolic posterior, a distribution for which it is easy to calculate quantiles and moments, provided that they exist. We derive the constraints on the prior parameters that yields finite posterior moments of order r. For the quadratic and relative quadratic loss functions, we investigate the choice of prior parameters leading to Bayes estimators with optimal frequentist mean square error. For the estimation of the lognormal mean we show, using simulation, that the Bayes estimator under quadratic loss compares favorably in terms of frequentist mean square error to known estimators. The theory does not apply only to the mean or median estimation but to all parameters that may be written as the exponential of a linear combination of the distribution's two.
    Keywords: Bayes estimators, generalized hyperbolic distribution, generalized inverse gamma distribution, Bessel functions. Stimatori bayesiani, distribuzione iperbolica generalizzata, distribuzione gamma inversa generalizzata,funzioni di Bessel
    Date: 2011
  2. By: Huber, Martin; Mellace, Giovanni
    Abstract: In many empirical problems, the evaluation of treatment effects is complicated by sample selection such that the outcome is only observed for a non-random subpopulation. In the absence of instruments and/or tight parametric assumptions, treatment effects are not point identified, but can be bounded under mild restrictions. Previous work on partial identification has primarily focused on the "always selected" (whose outcomes are observed irrespective of the treatment). This paper complements those studies by considering further populations, namely the "compliers" (whose selection states react to the treatment) and the selected population. We derive sharp bounds under various assumptions (monotonicity and stochastic dominance) and provide an empirical application to a school voucher experiment.
    Keywords: Causal inference, principal stratification, nonparametric bounds, sample selection
    JEL: C14 C21 C24
    Date: 2011–08
  3. By: Yin Liao; Heather M. Anderson
    Abstract: This paper proposes a new test for simultaneous intraday jumps in a panel of high frequency financial data. We utilize intraday first-high-low-last values of asset prices to construct estimates for the cross-variation of returns in a large panel of high frequency financial data, and then employ these estimates to provide a first-high-low-last price based test statistic to detect common large discrete movements (co-jumps). We study the finite sample behavior of our first-high-low-last price based test using Monte Carlo simulation, and find that it is more powerful than the Bollerslev et al (2008) return-based co-jump test. When applied to a panel of high frequency data from the Chinese mainland stock market, our first-high-low-last price based test identifies more common jumps than the return-based test in this emerging market.
    Keywords: Covariance, Co-jumps, High-frequency data, First-High-Low-Last price, Microstructure bias, Nonsynchronous trades, Realized covariance, Realized co-range.
    JEL: C12 C22 C32 G12 G14
    Date: 2011–08–18
  4. By: Yane, Shinji; Berg, Sanford
    Abstract: This paper examines the robustness of efficiency score rankings across four distributional assumptions for trans-log stochastic production-frontier models, using data from 1,221 Japanese water utilities (for 2004 and 2005). One-sided error terms considered include the half-normal, truncated normal, exponential, and gamma distributions. Results are compared for homoscedastic and doubly heteroscedastic models, where we also introduce a doubly heteroscedastic variable mean model, and examine the sensitivity of the nested models to a stronger heteroscedasticity correction for the one-sided error component. The results support three conclusions regarding the sensitivity of efficiency rankings to distributional assumptions. When four standard distributional assumptions are applied to a homoscedastic stochastic frontier model, the efficiency rankings are quite consistent. When those assumptions are applied to a doubly heteroscedastic stochastic frontier model, the efficiency rankings are consistent when proper and sufficient arguments for the variance functions are included in the model. When a more general model, like a variable mean model is estimated, efficiency rankings are quite sensitive to heteroscedasticity correction schemes.
    Keywords: stochastic production frontier models; Japanese water utilities; heteroscedasticity
    JEL: L95 C20
    Date: 2011
  5. By: D'Agostino, Antonello; McQuinn, Kieran; O'Brien, Derry
    Abstract: In this paper we present a dynamic factor model that produces nowcasts and backcasts of Irish quarterly GDP using timely data from a panel dataset of 35 indicators. We apply a recently developed methodology, whereby numerous potentially useful indicator series for Irish GDP can be availed of in a parsimonious manner and the unsynchronized nature of the release calendar for a wide range of higher frequency indicators can be handled. The nowcasts in this paper are generated by using dynamic factor analysis to extract common factors from the panel dataset. Bridge equations are then used to relate these factors to quarterly GDP estimates. We conduct an out-of-sample forecasting simulation exercise, where the performance of the factor model is compared with that of a standard benchmark model.
    Keywords: GDP; Forecasting; Factors
    JEL: C53 E52 C33
    Date: 2011
  6. By: Agustín Maravall Herrero (Banco de España); Domingo Pérez Cañete (Banco de España)
    Abstract: The recent economic crisis has altered the dynamics of economic series and, as a consequence, introduced uncertainty in seasonal adjustment of recent years. This problem was discussed in recent workshops at the European Central Bank and at Eurostat in the context of adjustment of the Euro Area Industrial Production (EPI) series. Because a seasonal component is unobserved and undefi ned, it is diffi cult to compare results from different adjustment methods. Within the regARIMA model-based approach, however, a framework for systematic analysis and comparison of results is indeed present. The EPI series is analyzed under the TRAMO-SEATS framework. The purpose of the analysis is not to compare alternative methods, but to show how the results of the model-based analysis can be exploited at the identifi cation, diagnostics, and inference stages of modeling, and in the selection of an appropiate seasonal adjustment (and underlying model). Despite the uncertainty induced by the crisis (and the revisions to the unadjusted data), the automatic procedure, with ramps to capture the spectacular 2008 drop in the series, provides excellent and stable results.
    Keywords: Time series analysis, Seasonal adjustment, Regression-ARIMA models, Filtering and smoothing, program TSW
    JEL: C22 C52 C87
    Date: 2011–07
  7. By: Peter Behl; Holger Dette; Manuel Frondel; Harald Tauchmann
    Abstract: In contrast to conventional model selection criteria, the Focused Information Criterion (FIC) allows for purpose-specifi c choice of models. This accommodates the idea that one kind of model might be highly appropriate for inferences on a particular parameter, but not for another. Ever since its development, the FIC has been increasingly applied in the realm of statistics, but this concept appears to be virtually unknown in the economic literature. Using a classical example and data for 35 U.S. industry sectors (1960–2005), this paper provides for an illustration of the FIC and a demonstration of its usefulness in empirical applications.
    Keywords: Information Criteria; translog cost function; cross-price elasticities
    JEL: C3 D2
    Date: 2011–06
  8. By: Alberto Bisin; Andrea Moro; Giorgio Topa
    Abstract: We study a general class of models with social interactions that might display multiple equilibria. We propose an estimation procedure for these models and evaluate its efficiency and computational feasibility relative to different approaches taken to the curse of dimensionality implied by the multiplicity. Using data on smoking among teenagers, we implement the proposed estimation procedure to understand how group interactions affect health-related choices. We find that interaction effects are strong both at the school level and at the smaller friends-network level. Multiplicity of equilibria is pervasive at the estimated parameter values, and equilibrium selection accounts for about 15 percent of the observed smoking behavior. Counterfactuals show that student interactions, surprisingly, reduce smoking by approximately 70 percent with respect to the equilibrium smoking that would occur without interactions.
    Keywords: Human behavior ; Social choice ; Health
    Date: 2011
  9. By: Majo, M.C.; Soest, A.H.O. van (Tilburg University, Center for Economic Research)
    Abstract: Response variables that are scored as counts and that present a large number of zeros often arise in quantitative health care analysis. We define a zero-in flated Poisson model with fixed-effects in both of its equations to identify respondent and health-related characteristics associated with health care demand. This is a new model that is proposed to model count measures of health care utilization and account for the panel structure of the data. Parameter estimation is achieved by conditional maximum likelihood. An application of the new model is implemented using micro level data from the 2004-2006 Survey of Health, Ageing and Retirement in Europe (SHARE), and compared to existing panel data models for count data. Results show that separately controlling for whether outcomes are zero or positive in one of the two years does make a difference for counts with a larger number of zeros.
    Keywords: Count Data;Zero-In ated Poisson Model;Fixed-effects;SHARE.
    JEL: J14 C14 C33
    Date: 2011
  10. By: Monfort, A.; Renne, J-P.
    Abstract: In this paper, we present a general discrete-time affine framework aimed at jointly modeling yield curves associated with different debtors. The underlying fixed-income securities may differ in terms of credit quality and/or in terms of liquidity. The risk factors follow conditionally Gaussian processes, with drifts and variance-covariance matrices that are subject to regime shifts described by a Markov chain with (historical) non-homogenous transition probabilities. While flexible, the model remains tractable. In particular, bond prices are given by quasi-explicit formulas. Various numerical examples are proposed, including a sector-contagion model and credit-rating modeling.
    Keywords: credit risk, liquidity risk, term structure, affine model, regime switching, Car process.
    JEL: E43 E44 E47 G12 G24
    Date: 2011
  11. By: Millimet, Daniel L. (Southern Methodist University); Roy, Jayjit (Appalachian State University)
    Abstract: The validity of existing empirical tests of the Pollution Haven Hypothesis (PHH) is constantly under scrutiny due to two shortcomings. First, the issues of unobserved heterogeneity and measurement error in environmental regulation are typically ignored due to the lack of a credible, traditional instrumental variable. Second, while the recent literature has emphasized the importance of geographic spillovers in determining the location choice of foreign investment, such spatial effects have yet to be adequately incorporated into empirical tests of the PHH. As a result, the impact of environmental regulations on trade patterns and the location decisions of multinational enterprises remains unclear. In this paper, we circumvent the lack of a traditional instrument within a model incorporating geographic spillovers utilizing three novel identification strategies. Using state-level panel data on inbound U.S. FDI, relative abatement costs, and other determinants of FDI, we consistently find (i) evidence of environmental regulation being endogenous, (ii) a negative impact of own environmental regulation on inbound FDI in pollution-intensive sectors, particularly when measured by employment, and (iii) larger effects of environmental regulation once endogeneity is addressed. Neighboring environmental regulation is not found to be an important determinant of FDI.
    Keywords: foreign direct investment, environmental regulation, spillovers, instrumental variables, control function, heteroskedasticity
    JEL: C31 F21 Q52
    Date: 2011–08
  12. By: Yucel, Eray
    Abstract: This note is intended to share some observations regarding a non-exhaustive collection of the early warning literature from 1971 to 2011. Evolution of the interest in early warning models, methodological spectrum of studies and coverage of economic variables are briefly discussed in addition to providing a bibliography.
    Keywords: Early warning systems; bibliometric analysis
    JEL: C00 Z00
    Date: 2011–08–18

This nep-ecm issue is ©2011 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.