Consider the problem of estimating the underlying regression function from a set of noisy data which is contaminated by a long-tailed error distribution. There exist several robust or resistant smoothing techniques. These techniques are turned out to ...
Consider the problem of estimating the underlying regression function from a set of noisy data which is contaminated by a long-tailed error distribution. There exist several robust or resistant smoothing techniques. These techniques are turned out to be very useful to reduce the influence of outlying observations. However, no matter what kind of robust smoother we use, we should choose the smoothing parameter. Relatively less attention has been made for the robust bandwidth selection method. In this paper, we adopt the idea of the robust location estimation technique and propose high breakdown cross-validation function and results from simulated data are shown.