[RsR] OGK covariance estimator

[Ruckstuhl Andreas (rks)]

Dear Martin

Many thanks for starting the discussion.

A few comments to your additional thoughts:

>> -----Ursprüngliche Nachricht-----
>> Von: r-sig-robust-bounces using r-project.org 
>> [mailto:r-sig-robust-bounces using r-project.org] Im Auftrag von 
>> Martin Maechler
>> Gesendet: Montag, 5. Dezember 2005 10:07
>> An: Peter Filzmoser
>> Cc: R-SIG-Robust using stat.math.ethz.ch
>> Betreff: Re: [RsR] OGK covariance estimator
>> 
>> Given the traffic on this list, 
>> and the not-yet-publication of the Treviso working group 
>> "minutes", let me open the topic to which I alluded above as
>> well: Our working group ("regression", later joined by
>> "econometrics") talked about the possibility and then 
>> desirability of an R package on "(basic) robust statitics" which
>> 
>>  1)  will be backed up by many `robustniks'
>>  2)  will remain focused, and hence (at least initially)
>>      primarily based on the methodology in the upcoming book 
>>      by Maronna, Martin and Yohai (=: MMY); and even from there,
>>      primarily on
>>       a) regression [including GLM, non-lin reg, maybe a bit more]
>>       b) multivariate : "location + scatter"
>>  3)  have quite a few authors (in the work group, we had 
>> some "commitments"),
>>      with me as coordinator and maintainer.
>>  4)  other "Robustness in R" packages would *build*
>>      (i.e. "Depend" in  R package lingo) on that basic package,
>>      and authors that contribute code from their own package
>>      would of course remain authors and would also keep the
>>      functions in their own packages (for a while at least; 
>> later their
>>      package will load or even attach the "basic robust"
>>      package, and hence have the functionality available indirectly).
>> 
>> -- more details are in the minutes of our workgroup(s) that I've
>>    sent to Matias {as Treviso co-organizer} to be put on the
>>    (Treviso RSR) webpage.
>> 
>> I think it would be great to get feedback from the 
>> R-SIG-robust audience on the above; particularly if you 
>> think that the idea is problematic or needs 
>> amendments/improvements before being workable.
>> 
>> Last week, I had added the following to (my latex version 
>> of) the minutes:
>> 
>> ------------------------
>> 
>>  Later notes -- by Martin Maechler, only
>>  ---------------------------------------
>> 
>>   o  Proposed names for the `basic robust statistics' package:
>>      1. robstats
>>      2. robbase
>>      3. baseRob
>> 
>>    I'm choosing the first one for now.

I good name for the packages is need. Some of the criteria should be that it should be intuitive, easy to remember and easy to find by google. I give slightly more preferences to a names starting with rob....

>> 
>>   o I've added (Rousseeuw & Croux)'s Qn and Sn estimators of
>>     scale, based on an R package I had started in 2002, which is
>>     based on the Fortran code from Antwerpen. 
>> 
>>   \item I plan to add ``\emph{psi - Function}'' objects, 
>> using an S4 class,
>>     with instances for Huber, Hampel, Biweight, etc, at least for the
>>     M-estimators (of location / regression).
>>     Such an object should contain  $\rho$, $\psi$, $w(x) := 
>> \psi(x)/x$,
>>     $\psi'$ (= $d/\mathrm{dx} \psi$) functions, default 
>> values for the tuning
>>     constants, and functionals such as $E_X[\psi(X)^2]$,  
>> $E_X[\psi'(X)]$,
>>     for $X\sim N(0,1)$ (these functionals are still 
>> \emph{functions} of the
>>     tuning parameters).

I support this approach; in particular that these objects should return more elements than the current versions in MASS. However, this objects are needed not just for linear regression models but also for GLMs. So I wonder whether there are alternatives for including the functionals (based on the normal case) in the same object.

Enclose, you find a temporary private package containing several functions. You are probably most interested in the robust fitting of Generalized Linear Models based on E. Cantoni and E. Ronchetti (2001). It is a new implementation. The fitting function is called rfglm(). There is also a function to compare two models: modsel.rfglm(). The name of this function is under revision. I going to call it anova (i.e. I will implement anova.rfglm()).

Talking about names: how should we call functions which do i.e. robust fitting of a glm:
	rfglm  (Robust Fitting of GLM)
	rglm
	robglm

Any comments to the naming or to the functions itself are very welcome.


>> 
>>     Very similarly, I'm interested also in the $\chi$ 
>> functions used for
>>     B-/V- optimal M-estimators of \emph{scale}, both the 
>> monotone and the
>>     redescending ones.
>> 
>>     In general, I think we should add ``\textbf{basic M-estimation}''
>>     things to the package as well, similar to, but
>>     more general than \code{MASS::huber}; note that I'd like to
>>     contribute \code{sfsmisc::huberM} (my `improved' \code{huber})
>>     to the \pkg{robstats} as well.
>> 
>> ------------------------
>> 
>> and actually I've done the S4 class for "psi-function" 
>> objects last Friday.

Great! 
>> 
>> Now I'm interested to hear more..
>> Martin


All the best
Andreas
>> 
>> _______________________________________________
>> R-SIG-Robust using r-project.org mailing list 
>> https://stat.ethz.ch/mailman/listinfo/r-sig->> robust
>> 



-------------- next part --------------
A non-text attachment was scrubbed...
Name: RobFit_0.2.1.zip
Type: application/x-zip-compressed
Size: 139091 bytes
Desc: RobFit_0.2.1.zip
URL: <https://stat.ethz.ch/pipermail/r-sig-robust/attachments/20051207/1a0903fe/attachment.bin>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: RobFit_0.2.1.tar.gz
Type: application/x-gzip
Size: 25777 bytes
Desc: RobFit_0.2.1.tar.gz
URL: <https://stat.ethz.ch/pipermail/r-sig-robust/attachments/20051207/1a0903fe/attachment-0001.bin>