"AcronymAttic.com

# What does CAN stand for?

## CAN stands for consistent and asymptotically normal

Estimators of ß based on incorrect parameterization of ? are generally inconsistent, whereas consistent nonparametric estimators deviate from ß by a larger probability order than N-1/2, where N is sample size. An estimator generalizing the ordinary least squares estimator of ß is constructed by inserting nonparametric regression estimators in the nonlinear orthogonal projection on Z. Under regularity conditions ß^ is shown to be $N^{1/2}\text{-consistent}$ for ß and asymptotically normal.