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: RE: Fixed Effects Form of Quantile Regression


From   Charles Koss <[email protected]>
To   [email protected]
Subject   Re: st: RE: Fixed Effects Form of Quantile Regression
Date   Wed, 30 Mar 2011 07:25:04 -0500

You are welcome, and thank you for the interesting  reading.

Charles

--
Charles Koss
http://charlesonnet.blogspot.com


On Tue, Mar 29, 2011 at 5:02 PM, inggrid <[email protected]> wrote:
> Hi,
> Thank you for the warning.
> I'll increase the number of replications.
> Please do read this article:
> http://www.stata.com/support/faqs/stat/reps.html
> \\ Inggrid
> --- On Wed, 3/30/11, Charles Koss <[email protected]> wrote:
>
>> From: Charles Koss <[email protected]>
>> Subject: Re: st: RE: Fixed Effects Form of Quantile Regression
>> To: [email protected]
>> Date: Wednesday, March 30, 2011, 4:38 AM
>> Now I wonder, having 17000
>> observations, did you find differences in
>> the results with 100 reps.? if positive, what is causing
>> such
>> differences?
>>
>> Charles
>>
>> --
>> Charles Koss
>> http://charlesonnet.blogspot.com
>>
>> On Tue, Mar 29, 2011 at 12:48 PM, inggrid <[email protected]>
>> wrote:
>> > Dear all,
>> >
>> > I have solved my problem.
>> > Here is the commands I used:
>> >
>> > set mem 500m
>> > set maxvar 10000
>> >
>> > keep y x1 x2 x3 (to save space)
>> >
>> > xi: bsqreg  y x1 x2 x3  i.id, quantile(.1)
>> reps(100)
>> >
>> >
>> > Many thanks to Jan and Jorge for their help.
>> >
>> >
>> > Best regards,
>> > Inggrid
>> > --- On Tue, 3/29/11, Jorge Eduardo Pérez Pérez
>> <[email protected]>
>> wrote:
>> >
>> >> From: Jorge Eduardo Pérez Pérez <[email protected]>
>> >> Subject: Re: st: RE: Fixed Effects Form of
>> Quantile Regression
>> >> To: "[email protected]"
>> <[email protected]>
>> >> Date: Tuesday, March 29, 2011, 10:10 PM
>> >> Try -bsqreg-:
>> >>
>> >> clear
>> >> set obs 10000
>> >> gen id=round(_n/100)
>> >> foreach x in v1 v2 v3 {
>> >>     gen `x'=uniform()
>> >> }
>> >> xi: bsqreg v1 v2 v3 i.id, quantile(0.1) reps(200)
>> >>
>> >>
>> >> _______________________
>> >> Jorge Eduardo Pérez Pérez
>> >>
>> >>
>> >>
>> >>
>> >> On Tue, Mar 29, 2011 at 9:56 AM, inggrid <[email protected]>
>> >> wrote:
>> >> > Hi Jan,
>> >> >
>> >> > Sorry, it seems I have been confused you. I
>> am quite
>> >> new with quantile regression.
>> >> >
>> >> > Actually, I would like to perform a fixed
>> effect
>> >> quantile regression in STATA.I heard that STATA
>> does not
>> >> provide correct standard errors for xi:qreg. So, I
>> try to
>> >> get boostrap standard errors. Please correct me if
>> I am
>> >> wrong.
>> >> >
>> >> > I have 17000 observations.
>> >> >
>> >> > Thank you very much for your help!
>> >> >
>> >> > Best regards,
>> >> >
>> >> > Inggrid
>> >> >
>> >> > --- On Tue, 3/29/11, Jan Bryla <[email protected]>
>> >> wrote:
>> >> >
>> >> >> From: Jan Bryla <[email protected]>
>> >> >> Subject: RE: [BULK]  Re: st: RE: Fixed
>> Effects
>> >> Form of Quantile Regression
>> >> >> To: "[email protected]"
>> >> <[email protected]>
>> >> >> Date: Tuesday, March 29, 2011, 8:31 PM
>> >> >> No, sorry - this is not clear to me.
>> >> >> Where do you experience problems exactly
>> - are you
>> >> actually
>> >> >> able to perform the quantile regression
>> or does
>> >> the error
>> >> >> appear when you bootstrap?
>> >> >>
>> >> >> You say you have 321 dummy variables.
>> This does
>> >> not sound
>> >> >> like a lot to me - are there are
>> observations
>> >> enough for
>> >> >> this?
>> >> >>
>> >> >> /Jan
>> >> >>
>> >> >> -----Original Message-----
>> >> >> From: inggrid [mailto:[email protected]]
>> >> >>
>> >> >> Sent: 29. marts 2011 12:23
>> >> >> To: [email protected]
>> >> >> Cc: Jan Bryla
>> >> >> Subject: [BULK] Re: st: RE: Fixed Effects
>> Form of
>> >> Quantile
>> >> >> Regression
>> >> >> Importance: Low
>> >> >>
>> >> >> Hi Jan,
>> >> >>
>> >> >> Thank you very much for your tips!
>> >> >> I have tried your suggestion.
>> Unfortunately,I have
>> >> 321
>> >> >> dummy variables. Hence, STATA could not
>> continued
>> >> my qreg
>> >> >> even if I have increased the memory space
>> and
>> >> the
>> >> >> variable (I was trying to get bootstrap
>> standard
>> >> errors as
>> >> >> well!).
>> >> >>
>> >> >> Here is my commands:
>> >> >>
>> >> >> capture program drop bootqreg
>> >> >> prog bootqreg
>> >> >> xi: qreg  y x1 x2 x3 i.hhid
>> >> >> [aweight=hhweight],quantile(0.1)
>> >> >> end
>> >> >> bs, reps(200) cluster(ea): bootqreg
>> >> >>
>> >> >> Any idea how to get the correct standard
>> error?
>> >> >>
>> >> >> Many thanks for the help!
>> >> >>
>> >> >> Best regards,
>> >> >> Inggrid
>> >> >>
>> >> >> --- On Tue, 3/29/11, Jan Bryla <[email protected]>
>> >> >> wrote:
>> >> >>
>> >> >> > From: Jan Bryla <[email protected]>
>> >> >> > Subject: st: RE: Fixed Effects Form
>> of
>> >> Quantile
>> >> >> Regression
>> >> >> > To: "[email protected]"
>> >> >> <[email protected]>
>> >> >> > Date: Tuesday, March 29, 2011, 2:22
>> PM
>> >> >> > A good starting point would be to
>> >> >> > perform least-squares dummy
>> variables
>> >> regression with
>> >> >> -qreg-
>> >> >> > or similar, such as
>> >> >> >
>> >> >> > xi: qreg y x1 x2 ... i.id
>> >> >> >
>> >> >> > Wich would give you "id"-fixed
>> effects.
>> >> >> >
>> >> >> > See also http://www.stata.com/statalist/archive/2004-07/msg00861.html
>> >> >> > and the following discussion.
>> >> >> >
>> >> >> > Hope it helps.
>> >> >> > Jan Bryla
>> >> >> >
>> >> >> >
>> >> >> > -----Original Message-----
>> >> >> > From: [email protected]
>> >> >> > [mailto:[email protected]]
>> >> >> > On Behalf Of inggrid
>> >> >> > Sent: 29. marts 2011 08:05
>> >> >> > To: [email protected]
>> >> >> > Subject: st: Fixed Effects Form of
>> Quantile
>> >> >> Regression
>> >> >> >
>> >> >> > Dear all,
>> >> >> >
>> >> >> > I am going to use a fixed effect
>> quantile
>> >> regression.
>> >> >> Does
>> >> >> > anyone know the STATA code for this
>> method?
>> >> >> >
>> >> >> > Thank you very much for your help.
>> >> >> >
>> >> >> > Best regards,
>> >> >> > Inggrid
>> >> >> >
>> >> >> >
>> >> >> >
>> >> >> > *
>> >> >> > *   For searches and help try:
>> >> >> > *   http://www.stata.com/help.cgi?search
>> >> >> > *   http://www.stata.com/support/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/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/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/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/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/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/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/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/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


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