** Next:** MEDIANS AND REGRESSION
** Up:** Claerbout: Medians in regression
** Previous:** Claerbout: Medians in regression

Here I design filters and models of hyperbola superposition
based on medians.
Let *r*_{i} be a residual and be a residual
perturbation caused by a change
in the model
.With ,choosing gives us residuals where as many components as possible
of the residual are pushed towards zero.
This procedure suggests a family of processes
that should be immune to bursty noises in data
and might quickly give good approximations
for inversions of high dimensionality.

** Next:** MEDIANS AND REGRESSION
** Up:** Claerbout: Medians in regression
** Previous:** Claerbout: Medians in regression
Stanford Exploration Project

11/12/1997