Errors-in-variables models: a generalized functions approach - Statistics > MethodologyReport as inadecuate




Errors-in-variables models: a generalized functions approach - Statistics > Methodology - Download this document for free, or read online. Document in PDF available to download.

Abstract: Identification in errors-in-variables regression models was recently extendedto wide models classes by S. Schennach Econometrica, 2007 S via use ofgeneralized functions. In this paper the problems of non- and semi- parametricidentification in such models are re-examined. Nonparametric identificationholds under weaker assumptions than in S; the proof here does not rely ondecomposition of generalized functions into ordinary and singular parts, whichmay not hold. A consistent nonparametric plug-in estimator for regressionfunctions in the space of absolutely integrable functions constructed.Semiparametric identification via a finite set of moments is shown to hold forclasses of functions that are explicitly characterized; unlike S existence ofa moment generating function for the measurement error is not required.



Author: Victoria Zinde-Walsh

Source: https://arxiv.org/







Related documents