I made this plot for my M-estimation library, but I think the image nicely showcases how the various loss functions for robust mean/regression penalize the errors (of the 1st deriv of log-L)
no penalty would be a diagonal line with a slope of 1
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.
no penalty would be a diagonal line with a slope of 1