Next: Particular Robust Estimates
Up: 5: Goodness of
Previous: Likelihood Based Robust
- Now, as we are assuming p to be an even function of z, i.e.,
symmetric about the mean, we write the above as

- where
is an odd function of its argument.
- For the case of Gaussian p,
-
is just
and Equation (37) is

- which gives the arithmetic mean as the maximum likelihood
estimate of the mean.
Geoffrey Fox, Northeast Parallel Architectures Center at Syracuse University, gcf@npac.syr.edu