The impact of a Hausman pretest on the size of a hypothesis test: The panel data case

Guggenberger, Patrik

doi:10.1016/j.jeconom.2009.11.003

Cited by 62 publications

(33 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When all remaining covariates are relevant, the result of Theorem 2 applies. However, as a referee correctly points out, pretesting itself gives rise to problems for subsequent inference, as discussed in Guggenberger (2010). Therefore, a preferred alternative is to use bootstrap methods for approximating the finite‐sample distribution of .…”

Section: Semiparametric Kernel Estimation Of Varying‐coefficient Mmentioning

confidence: 99%

Categorical semiparametric varying‐coefficient models

Ouyang

Racine

2011

J of Applied Econometrics

View full text Add to dashboard Cite

SUMMARYSemiparametric varying‐coefficient models have become a common fixture in applied data analysis. Existing approaches, however, presume that those variables affecting the coefficients are continuous in nature (or that there exists at least one such continuous variable) which is often not the case. Furthermore, when all variables affecting the coefficients are categorical/discrete, theoretical underpinnings cannot be obtained as a special case of existing approaches and, as such, requires a separate treatment. In this paper we use kernel‐based methods that place minimal structure on the underlying mechanism governing parameter variation across categorical variables while providing a consistent and efficient approach that may be of interest to practitioners. One area where such models could be particularly useful is in settings where interactions among the categorical and real‐valued predictors consume many (or even exhaust) degrees of freedom for fully parametric models (which is frequently the case in applied settings). Furthermore, we demonstrate that our approach behaves optimally when in fact there is no variation in a model's coefficients across one or more of the categorical variables (i.e. the approach pools over such variables with a high probability). An illustrative application demonstrates potential benefits for applied researchers. Copyright © 2011 John Wiley & Sons, Ltd.

show abstract

Section: Semiparametric Kernel Estimation Of Varying‐coefficient Mmentioning

confidence: 99%

Categorical semiparametric varying‐coefficient models

Ouyang

Racine

2011

J of Applied Econometrics

View full text Add to dashboard Cite

show abstract

“…The RE estimates are associated with smaller standard errors, resulting in statistically significant estimates for political risk variables in a few instances where the FE and GMM estimates are insignificant. However, Guggenberger (2010) shows that standard tests of statistical significance conditional on non-rejection of orthogonality by the Hausman test can be highly misleading in finite samples when there is moderate correlation between the country effects and regressors. (Monte Carlo simulations are run assuming a panel structure and correlations that closely match features of our data.…”

Section: Model Specificationmentioning

confidence: 99%

Expropriation risk and FDI in developing countries: Does return of capital dominate return on capital?

Akhtaruzzaman

Berg

Hajzler

2017

European Journal of Political Economy

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. ii Terms of use: Documents in EconStor may AbstractPreviously reported effects of institutional quality and political risks on foreign direct investment (FDI) are mixed and, therefore, difficult to interpret. We present empirical evidence suggesting a relatively clear, statistically robust, and intuitive characterization. Institutional factors that affect the likelihood of an abrupt and total loss of foreigners' capital (i.e., return of capital) dominate those that affect rates of return conditional on a strictly positive terminal investment value (i.e., return on capital). A one-standarddeviation reduction in expropriation risk is associated with a 72 per cent increase in FDI, which is substantially larger than the effects of any other dimensions of institutional quality simultaneously controlled for in our empirical models of FDI inflows. This evidence is consistent with the predictions of a standard theory of FDI under imperfect contract enforcement. We show in the context of a simple model with endogenous expropriation that, when there is a binding threat of expropriation, foreign investors can become unresponsive to differences in other dimensions of institutions and political risk, and may even reduce optimal investment as these institutions improve. Bank topics: Development economics, International financial markets JEL codes: D23, F21, F23 RésuméLes effets signalés antérieurement qu'exercent la qualité des institutions et les risques politiques sur l'investissement direct étranger (IDE) sont contrastés et, par conséquent, difficiles à interpréter. Nous présentons des données empiriques qui font ressortir une caractérisation intuitive statistiquement solide. Les facteurs institutionnels ayant une incidence sur la probabilité d'une perte soudaine et totale du capital détenu par des étrangers (remboursement de capital) l'emportent sur ceux touchant les taux de rendement subordonnés à une valeur nue finale strictement positive (rendement du capital investi). Une réduction de un écart-type du risque d'expropriation est associée à une augmentation de 72 % de l'IDE, une hausse nettement supérieure à celles engendrées par n'importe quels autres aspects de la qualité des institutions pris en compte simultanément dans nos modèles empiriques d'entrées d'IDE. Ce résultat cadre avec les prédictions d'une théorie classique de l'IDE où l'exécution des contrats est imparfaite. Dans un modèle simple intégrant un facteur d'expropriation endogène, nous démontrons qu...

show abstract

“…Previous analyses of the effect of a Hausman pretest on either a hypothesis test (GUGGENBERGER, ) or a confidence interval (K ABAILA , M AINZER and F ARCHIONE , ) for the slope parameter have been carried out unconditionally. These analyses are restricted to particular DGPs for the covariate.…”

Section: Introductionmentioning

confidence: 99%

Conditional assessment of the impact of a Hausman pretest on confidence intervals

Kabaila

Mainzer

Farchione

2017

Statistica Neerlandica

View full text Add to dashboard Cite

We assess the impact of a Hausman pretest, applied to panel data, on a confidence interval for the slope, conditional on the observed values of the time-varying covariate. This assessment has the advantages that it (a) relates to the values of this covariate at hand, (b) is valid irrespective of how this covariate is generated, (c) uses finite sample results and (d) results in an assessment that is determined by the values of this covariate and only 2 unknown parameters. Our conditional analysis shows that the confidence interval constructed after a Hausman pretest should not be used.2

show abstract

The impact of a Hausman pretest on the size of a hypothesis test: The panel data case

Cited by 62 publications

References 21 publications

Categorical semiparametric varying‐coefficient models

Categorical semiparametric varying‐coefficient models

Expropriation risk and FDI in developing countries: Does return of capital dominate return on capital?

Conditional assessment of the impact of a Hausman pretest on confidence intervals

Contact Info

Product

Resources

About