Outlier-Resistant 𝐿_𝟏 Orthogonal Regression via the Reformulation-Linearization Technique

Figure 3

Examples of data sets used in simulation experiments and fitted models: (a) a data set with vertical outliers generated using parameters 𝑚=10 and 𝐶=25, (b) a data set with clustered leverage outliers with 𝑛=100 and generated using 𝜖=0.25, and (c) a data set with errors in both variables sampled from a Laplace distribution with 𝑛=200.

(a)

(b)

(c)