Statistical inference in EV linear model

Abstract

Regression calibration estimation procedure is proposed in linear errors-in-variables regression model when the measurement error follows a normal distribution. The improvement is made feasible by the Tweedie’s formula. Large sample properties, including the weak consistency and the asymptotic normality are established under some mild conditions. Simulation studies are conducted to evaluate the finite sample performances via comparing with existing estimation methods.

Keywords:

• Normal measurement error
• Kernel estimate
• Tweedie’s formula

Additional information

Funding

The authors are very pleased to thank the editor, an associated editor and reviewers for their helpful suggestions and comments. This research was supported by the National Natural Science Foundation of China10.13039/501100001809 (Grant No. 12071267).