Outlier-Resistant Orthogonal Regression via the Reformulation-Linearization Technique
Figure 1
Two-dimensional illustration of different methods for incorporating the norm into orthogonal regression. In traditional orthogonal regression, the sum of distances of points to is maximized, the sum of distances of points to is minimized, and the sum of the magnitudes of is maximized. As noted in the text, each of these distance measures can be modified to incorporate the norm to derive different results. In this paper, the approach is to maximize the sum of distances of points to which is illustrated by .