ON THE INFLUENTIAL POINTS IN THE FUNCTIONAL CIRCULAR RELATIONSHIP MODELS WITH AN APPLICATION ON WIND DATA

Abstract

If the interest is to calibrate two instruments then the functional relationship model is more appropriate than regression models. Fitting a straight line when both variables are circular and subject to errors has not received much attention. In this paper, we consider the problem of detecting influential points in two functional relationship models for circular variables. The first is based on the simple circular regression the (SC), while the last is derived from the complex linear regression