Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: fit robust regression


From   Steve Samuels <[email protected]>
To   [email protected]
Subject   Re: st: fit robust regression
Date   Wed, 19 Feb 2014 19:26:36 -0500

For a reference, see:

http://hsphsun3.harvard.edu/cgi-bin/lwgate/STATALIST/archives/statalist.1302/Subject/article-428.html



Steve
[email protected]

On Feb 19, 2014, at 8:45 AM, Nick Cox <[email protected]> wrote:

Having been rude about -rreg- I should be more positive:

Quantile regression I would regard as potentially robust regression,
(Elsewhere I got a lot of flak for saying that, hinging on a
quasi-religious dispute on the real, essential, or correct meaning of
"robust".)

Otherwise work much closer to the state of the art on robust
regression in Stata is typically associated with Vincenzo Verardi.

Nick
[email protected]


On 19 February 2014 13:40, Michael Riechert
<[email protected]> wrote:
> Thank you Nick for that remark. I´ll definitely have a conscious look on that method.
> Regards, Michael
> 
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of Nick Cox
> Sent: Mittwoch, 19. Februar 2014 14:34
> To: [email protected]
> Subject: Re: st: fit robust regression
> 
> You sent this before. Once is enough: please see the Statalist FAQ on repeated posts.
> 
> -rregfit- is from http://www.ats.ucla.edu/stat/stata/ado/analysis
> Please remember to explain where user-written programs you refer to come from. (That applies to -esttab- too.)
> 
> If -rregfit- doesn't leave something behind, your only real option is probably to clone the code and add further calculations.
> 
> I would be wary of using -rreg- for anything much for reasons outlined e.g. in http://www.stata.com/statalist/archive/2011-01/msg00416.html If they don't apply to your project, so much the better.
> Nick
> [email protected]
> 
> 
> On 19 February 2014 13:19, Michael Riechert <[email protected]> wrote:
>> Dear Stata community,
>> 
>> I惴 wondering whether it is possible to store certain variables of the output from the command rregfit. I am doing a bunch of robust regressions applying a loop and summarize all estimates using the command esttab. It would be perfect if I can display the adjusted R-squared and the BIC as additional line within the final table using esttab. But so far, I don愒 figure out how to store the R-square and the BIC out of the rregfit output. I appreciate every hint. Thank you!
>> 
>> Best regards,
>> Michael
>> 
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>> *   http://www.ats.ucla.edu/stat/stata/
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index