Resource title

Robust adaptive estimation of dimension reduction space

Resource image

image for OpenScout resource :: Robust adaptive estimation of dimension reduction space

Resource description

Most dimension reduction methods based on nonparametric smoothing are highly sensitive to outliers and to data coming from heavy tailed distributions. We show that the recently proposed MAVE and OPG methods by Xia et al. (2002) allow us to make them robust in a relatively straightforward way that preserves all advantages of the original approach. The best of the proposed robust modifications, which we refer to as MAVE-WMAD-R, is sufficiently robust to outliers and data from heavy tailed distributions, it is easy to implement, and surprisingly, it also outperforms the original method in small sample behaviour even when applied to normally distributed data.

Resource author

Pavel Clzek, Wolfgang Härdle

Resource publisher

Resource publish date

Resource language


Resource content type


Resource resource URL

Resource license

Adapt according to the presented license agreement and reference the original author.