Redescending M-estimator - Advantages

Advantages

Redescending M-estimators have high breakdown points (close to 0.5), and their Ψ function can be chosen to redescend smoothly to 0. This means that moderately large outliers are not ignored completely, and greatly improves the efficiency of the redescending M-estimator.

The redescending M-estimators are slightly more efficient than the Huber estimator for several symmetric, wider tailed distributions, but about 20% more efficient than the Huber estimator for the Cauchy distribution. This is because they completely reject gross outliers, while the Huber estimator effectively treats these the same as moderate outliers.

As other M-estimators, but unlike other outlier rejection techniques, they do not suffer from masking effects.

Read more about this topic:  Redescending M-estimator

Famous quotes containing the word advantages:

    There is no one thoroughly despicable. We cannot descend much lower than an idiot; and an idiot has some advantages over a wise man.
    William Hazlitt (1778–1830)

    ... is it not clear that to give to such women as desire it and can devote themselves to literary and scientific pursuits all the advantages enjoyed by men of the same class will lessen essentially the number of thoughtless, idle, vain and frivolous women and thus secure the [sic] society the services of those who now hang as dead weight?
    Sarah M. Grimke (1792–1873)

    If we help an educated man’s daughter to go to Cambridge are we not forcing her to think not about education but about war?—not how she can learn, but how she can fight in order that she might win the same advantages as her brothers?
    Virginia Woolf (1882–1941)