UNIGE document Scientific Article
previous document  unige:73272  next document
add to browser collection

Specification Testing when the Null is Nonparametric or Semiparametric

Rodríguez-Póo, Juan Manuel
Vieu, Philippe
Published in Econometric Theory. 2015, p. 1281-1309
Abstract This paper discusses the problem of testing misspeci_cations in semiparametric regression models for a large family of econometric models under rather general conditions. We focus on two main issues that typically arise in econometrics. First, many econometric models are estimated through maximum likelihood or pseudo-ML methods like, for example, limited dependent variable or gravity models. Second, often one might not want to fully specify the null hypothesis. Instead, one would rather impose some structure like separability or monotonicity. In order to address these points we introduce an adaptive omnibus test. Special emphasis is given to practical issues like adaptive bandwidth choice, general but simple requirements on the estimates, and _nite sample performance, including the resampling approximations.
Keywords Specification testSemiparametric econometricsAdaptive testingLimited dependent variablesSeparability
Full text
Article (Author postprint) (374 Kb) - document accessible for UNIGE members only Limited access to UNIGE
Other version: http://dx.doi.org/10.1017/S0266466614000504
(ISO format)
RODRÍGUEZ-PÓO, Juan Manuel, SPERLICH, Stefan Andréas, VIEU, Philippe. Specification Testing when the Null is Nonparametric or Semiparametric. In: Econometric Theory, 2015, p. 1281-1309. https://archive-ouverte.unige.ch/unige:73272

307 hits



Deposited on : 2015-06-22

Export document
Format :
Citation style :