Hi there,
I have finally decided to include the MM-estimator in my Data Analysis
course and so I again had to think about it and its implementation a bit.
Apparently the scale estimator given out by lmrob is the S-scale. One could
wonder whether the optimal value of the final MM-sum multiplied by a
suitable factor to get consistency under normality would be a more
appropriate scale estimator because it is directly associated to the
MM-estimator (which we eventually use in most situations) rather than
to the S-estimator.
Wouldn't it be good to give this out as default scale estimator (or both)?
There could also be a control parameter specifying which scale is given
out.
Any thoughts?
Cheers,
Christian
*** --- ***
Christian Hennig
University College London, Department of Statistical Science
Gower St., London WC1E 6BT, phone +44 207 679 1698
[EMAIL PROTECTED], www.homepages.ucl.ac.uk/~ucakche
_______________________________________________
R-SIG-Robust@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-robust
