Show simple item record

dc.contributor.advisorPinto, Cristine
dc.contributor.authorCardoso, Murilo Sepulvida
dc.date.accessioned2020-07-02T18:11:46Z
dc.date.available2020-07-02T18:11:46Z
dc.date.issued2020-05-28
dc.identifier.urihttps://hdl.handle.net/10438/29393
dc.description.abstractThe biggest challenge of the instrumental variable model is finding a valid instrument, one that satisfies the assumptions of relevance and, especially, exogeneity. To impose a less restrictive assumption, some estimators combine unobservable effects with instrumental variables, as example IV-FE. In this paper, we study a large-panel instrumental variable model where the instrument may be correlated with unobservable variables, even when they vary across both dimensions. This variation implies that standard approaches in the literature, such as IV, IV-FE, and linear factor models (Pesaran, 2006; Bai, 2009), are inconsistent. We construct two and show their √ NT convergence under both large N and large T. Our exogeneity assumption is less restrictive than the standard instrumental variable model assumption since the instrument shall be exogenous given the factor structure. We show their asymptotic normality distribution for some rate of N/T even when the errors have autocorrelation and heteroskedasticity in both dimensions. We also study the trade-off between our estimators and a standard IV estimator when the error has an interactive fixed-effect structure, and the instrument is valid. In this case, we show that our estimator is more efficient than IV if the variance of the factor structure is sufficiently large than the error variance and less efficient if the variance of factor structure is sufficiently smaller.eng
dc.description.abstractThe biggest challenge of the instrumental variable model is finding a valid instrument, one that satisfies the assumptions of relevance and, especially, exogeneity. To impose a less restrictive assumption, some estimators combine unobservable effects with instrumental variables, as example IV-FE. In this paper, we study a large-panel instrumental variable model where the instrument may be correlated with unobservable variables, even when they vary across both dimensions. This variation implies that standard approaches in the literature, such as IV, IV-FE, and linear factor models (Pesaran, 2006; Bai, 2009), are inconsistent. We construct two and show their √ NT convergence under both large N and large T. Our exogeneity assumption is less restrictive than the standard instrumental variable model assumption since the instrument shall be exogenous given the factor structure. We show their asymptotic normality distribution for some rate of N/T even when the errors have autocorrelation and heteroskedasticity in both dimensions. We also study the trade-off between our estimators and a standard IV estimator when the error has an interactive fixed-effect structure, and the instrument is valid. In this case, we show that our estimator is more efficient than IV if the variance of the factor structure is sufficiently large than the error variance and less efficient if the variance of factor structure is sufficiently smaller.por
dc.language.isoeng
dc.subjectInstrumental variableeng
dc.subjectLinear factor modeleng
dc.subjectInteractive fixed-effect modeleng
dc.subjectEndogenous regressorseng
dc.subjectLarge paneleng
dc.subjectVariável instrumentalpor
dc.subjectModelo de efeitos fixos interativospor
dc.subjectRegressores endógenospor
dc.subjectDados em painelpor
dc.titleInstrumental variable with interactive fixed effectseng
dc.typeDissertationeng
dc.subject.areaEconomiapor
dc.contributor.unidadefgvEscolas::EESPpor
dc.subject.bibliodataAnálise de painelpor
dc.subject.bibliodataVariáveis instrumentais (Estatística)por
dc.subject.bibliodataAnálise fatorialpor
dc.subject.bibliodataModelos lineares (Estatística)por
dc.rights.accessRightsopenAccesseng
dc.contributor.memberFerman, Bruno
dc.contributor.memberFernandes, Marcelo
dc.contributor.memberMoreira, Marcelo J.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record