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: Re: Re: st: Putting Coefficients in the same column with esttab/estout
From
emanuele mazzini <[email protected]>
To
[email protected]
Subject
Re: Re: Re: st: Putting Coefficients in the same column with esttab/estout
Date
Fri, 29 Apr 2011 19:35:02 +0200
I will try to figure it out. Yes, I saw the Daniel Klein's post.
Thank you very much for your help.
Regards,
Emanuele.
2011/4/29 Johannes Geyer <[email protected]>:
> Thinking again about your problem, you could use esttab and refer to
> r(coefs) and then extract and repost the vectors
>
> You can cycle through your saved estimation results like Daniel Klein
> suggested in an earlier post,
>
> clear all
> sysuse auto
>
> reg price mpg trunk, nocons
> esttab, se
> matrix C1 = r(coefs)
>
> reg price weight, nocons
> esttab, se
> matrix C2 = r(coefs)
>
> matrix C = C1\C2
>
> matrix b = C[1....,1]'
> matrix se = C[1....,2]'
>
> ereturn post b
> estadd matrix se
>
> esttab, se
>
>
> johannes
>
>
> [email protected] schrieb am 28/04/2011 19:14:33:
>
>> You are right and your suggestion is what I thought, more or less. But
>> the point is that i should run all the regressions again, shouldn't I?
>> And this would took quite a long time for me.
>> Is there a way to type the command matrix without running them another
> time?
>>
>> 2011/4/28 Johannes Geyer <[email protected]>:
>> > I did not understand that you estimate six models and want to report
> only
>> > three columns - is that correct?
>> >
>> > If so, you have to tell esttab that the coefficients of models x and y
>> > belong to the same column, -order- is
>> > not designed to do that.
>> >
>> > Ben Jann provides an example on his webpage that is related in the
> sense
>> > that it shows how to change
>> > models and regressors in a table using Stata syntax
>> >
>> > http://repec.org/bocode/e/estout/advanced.html#advanced907
>> >
>> > The problem in your case is much simpler I guess. You have to -ereturn
>> > post- beta and se vectors and
>> > tabulate them, e.g.:
>> >
>> > ******************************************************
>> > sysuse auto
>> > reg mpg foreign weight, nocons
>> > matrix k = e(b)
>> > reg mpg rep78 trunk, nocons
>> > matrix k = k,e(b)
>> > ereturn post k
>> > eststo clear
>> > esttab
>> > *****************************************************
>> >
>> >
>> > Johannes
>> >
>> > ----------------------
>> > Johannes Geyer
>> > Deutsches Institut für Wirtschaftsforschung (DIW Berlin)
>> > German Institute for Economic Research
>> > Department of Public Economics
>> > DIW Berlin
>> > Mohrenstraße 58
>> > 10117 Berlin
>> > Tel: +49-30-89789-258
>> >
>> > [email protected] schrieb am 28/04/2011 17:45:30:
>> >
>> >> Yes, what you see is what I get with that, unfortunately.
>> >>
>> >> 2011/4/28 Johannes Geyer <[email protected]>:
>> >> > did you try the option -order-?
>> >> >
>> >> > esttab ... , order(lagvar1 avg5fvar lagvar2 avg5gvar...)
>> >> >
>> >> > Johannes
>> >> >
>> >> >
>> >> >
>> >> >
>> >> > ----------------------
>> >> > Johannes Geyer
>> >> > Deutsches Institut für Wirtschaftsforschung (DIW Berlin)
>> >> > German Institute for Economic Research
>> >> > Department of Public Economics
>> >> > DIW Berlin
>> >> > Mohrenstraße 58
>> >> > 10117 Berlin
>> >> > Tel: +49-30-89789-258
>> >> >
>> >> > [email protected] schrieb am 28/04/2011
> 16:55:52:
>> >> >
>> >> >> Dear all Stata users,
>> >> >> I have just finished running a lot of estimates that i have saved
> on
>> >> >> my computer with the command estwrite (after having stored them
> with
>> >> >> estimates store). Now it comes to make some tables, but with both
> the
>> >> >> commands esttab and estout I cannot let some coefficients stay in
> the
>> >> >> same column. I can be more precise with an example. What i get
> with
>> >> >> either esttab (or even estout) is:
>> >> >>
>> >> >>
>> >> >>
>> >> >
>> >>
>> >
>>
> ------------------------------------------------------------------------------------------------------------
>> >> >> (1) (2) (3)
>> >> >> (4) (5) (6)
>> >> >>
>> >> >
>> >>
>> >
>>
> ------------------------------------------------------------------------------------------------------------
>> >> >> lagpolity1 0.014***
>> >> >> (0.000)
>> >> >> lagpolity2 0.027***
>> >> >> (0.001)
>> >> >> avg5polity1
>> >> >> 0.015***
>> >> >>
>> >> >> (0.001)
>> >> >> avg5polity2
>> >> >> 0.028***
>> >> >>
>> >> >> (0.001)
>> >> >> lagfh1 0.054***
>> >> >> (0.002)
>> >> >> lagfh2 0.123***
>> >> >> (0.002)
>> >> >> avg5fh_opp1
>> >> >> 0.045***
>> >> >>
>> >> >> (0.002)
>> >> >> avg5fh_opp2
>> >> >> 0.114***
>> >> >>
>> >> >> (0.002)
>> >> >> lagchga1 0.112***
>> >> >> (0.007)
>> >> >> lagchga2 0.347***
>> >> >> (0.007)
>> >> >> avg5chga1
>> >> >> 0.116***
>> >> >>
>> >> >> (0.007)
>> >> >> avg5chga2
>> >> >> 0.352***
>> >> >>
>> >> >> (0.008)
>> >> >>
>> >> >>
>> >> >>
>> >> >> But what I'd like to get is the coefficients of all those that I
> call
>> >> >> avg5 below the coefficients of the lagged vars. In other words,
>> >> >> something like:
>> >> >>
>> >> >>
>> >> >>
>> >> >
>> >>
>> >
>>
> ------------------------------------------------------------------------------------------------------------
>> >> >> (1) (2) (3)
>> >> >> (4) (5) (6)
>> >> >>
>> >> >
>> >>
>> >
>>
> ------------------------------------------------------------------------------------------------------------
>> >> >> lagpolity1 0.014***
>> >> >> (0.000)
>> >> >> lagpolity2 0.027***
>> >> >> (0.001)
>> >> >> avg5polity1 0.015***
>> >> >> (0.001)
>> >> >> avg5polity2 0.028***
>> >> >> (0.001)
>> >> >> lagfh1 0.054***
>> >> >> (0.002)
>> >> >> lagfh2 0.123***
>> >> >> (0.002)
>> >> >> avg5fh_opp1 0.045***
>> >> >> (0.002)
>> >> >> avg5fh_opp2 0.114***
>> >> >> (0.002)
>> >> >> lagchga1 0.112***
>> >> >> (0.007)
>> >> >> lagchga2 0.347***
>> >> >> (0.007)
>> >> >> avg5chga1 0.116***
>> >> >> (0.007)
>> >> >> avg5chga2 0.352***
>> >> >> (0.008)
>> >> >>
>> >> >>
>> >> >> But obviously I do not want to run all the regressions again (it'd
>> >> >> take ages!!).
>> >> >>
>> >> >> Anyone can help me?
>> >> >>
>> >> >> Thanks to all of you for your time and consideration,
>> >> >>
>> >> >> Regards,
>> >> >>
>> >> >> Emanuele.
>> >> >> *
>> >> >> * 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/