Article ID Journal Published Year Pages File Type
5129827 Statistics & Probability Letters 2017 5 Pages PDF
Abstract

This paper finds that heteroskedasticity in nonclassical error-in-variable models leads to biased and inconsistent estimates when higher-order moments of data are used. A closed-form estimator is provided to correct this bias based on information from the first three moments.

Keywords
Related Topics
Physical Sciences and Engineering Mathematics Statistics and Probability
Preview
Closed-form estimation of a regression model with a mismeasured binary regressor and heteroskedasticity
Authors
, ,