[R-sig-finance] using yahoo and other data to calculate CAPM and FF betas

[Martin Maechler]

>>>>> "Krishna" == Krishna Kumar <kriskumar at earthlink.net>
>>>>>     on Thu, 06 Apr 2006 23:27:06 -0400 writes:

  .........

    Krishna> Also there was a very interesting paper that showed
    Krishna> that the Fama-French effect was not really a
    Krishna> anamoly when you estimate using Robust regression
    Krishna> instead of OLS. I can't remember the reference but
    Krishna> it was Doug Martin and someone else from UW ...  R
    Krishna> has some nice facilities with rrcov to do the
    Krishna> robust regressions!!

Apropos  "Robust regression":

- Note that 'rrcov' (by Valentin Todorov) has recently been merged
  into the new package "robustbase" -- and the latest rrcov
  version will be merged again.
  The goal of "robustbase" is to provide ``basic robust
  statistics'' to R -- additionally to what's already in 'stats'
  and 'MASS' and trying to be closer to the "state-of-the-art".
  The latest version of robustbase, 0.1-5 has "hit" CRAN yesterday
  and should become available more generally shortly.

  Additionally to the fast ltsReg() {from 'rrcov' originally}, 
  "robustbase" now also contains  lmrob(), implementing a
  "fast MM" estimator (based on fast-S) from Matias
  Salibian-Barreras and Victor Yohai.

- Further note that there's also a `young' R-SIG-robust mailing
  list with quite a few "robustniks" subscribed -- some of who
  do not read other R-lists AFAIK.

Martin Maechler, ETH Zurich