An estimation technique which is insensitive to small departures from the idealized assumptions which have been used to optimize the algorithm. Classes of such techniques include M-Estimate (which follow from maximum likelihood considerations), L-Estimate (which are linear combinations of Order Statistics), and R-Estimate (based on Rank tests).
See also L-Estimate, M-Estimate, R-Estimate
Press, W. H.; Flannery, B. P.; Teukolsky, S. A.; and Vetterling, W. T. ``Robust Estimation.'' §15.7 in
Numerical Recipes in FORTRAN: The Art of Scientific Computing, 2nd ed. Cambridge, England:
Cambridge University Press, pp. 694-700, 1992.