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: meanonly


From   Maarten Buis <[email protected]>
To   [email protected]
Subject   Re: st: meanonly
Date   Wed, 11 Apr 2012 15:29:16 +0200

I would probably rephrase the entire problem in terms of various
-predict-s after each model (the wage regression, the regress to get
the means, the -mlogit-). My guess would be that that is easiest to
program / debug, but you'll just have to find out if that is true by
trying it. That is programing: you use your intuition to guess what
would be easiest and than you try it (and find out you were wrong...).

If you insist on using matrices, than you can, but you need to worry
about not mixing up the column numbers

If you insist on using scalars, than you can, but you need to use
-tempname-s in order to avoid conflicts with variable names.

-- Maarten

On Wed, Apr 11, 2012 at 2:56 PM, Chiara Mussida <[email protected]> wrote:
> i have to use these means, together with the betas of a reg. More
> precisely, b are betas by occupation, whilst x are the mean of the
> variables in my dataset. To compute the total gender wage gap i have
> to compute this for each occupation:
> pf (xm-xf)bm + xmbm(pm-pf)+pfxf(bm-bf)+xmbm(pf -pm)
>
> m and f is for male and female. P are the predicted probability from a
> mlogit.b as said and asked yesterday are coef from wage reg.
> Thanks
>
> On 11/04/2012, Maarten Buis <[email protected]> wrote:
>> Haven't we been there before? I suggest you give us the complete story
>> as what is efficient depends on what you want to do with those means.
>>
>> On Wed, Apr 11, 2012 at 12:21 PM, Chiara Mussida <[email protected]> wrote:
>>> ok. What is the most efficient way to store the mean as scalars?
>>> Thanks
>>>
>>> On 10/04/2012, Maarten Buis <[email protected]> wrote:
>>>> On Tue, Apr 10, 2012 at 4:23 PM, Chiara Mussida wrote:
>>>>> su south, meanonly
>>>>> scalar variable = r(mean)
>>>>> gives me a scalar for the mean of variable south. Is there a way to
>>>>> gen scalars for the mean of the variable south by gender and
>>>>> occupation? I have 7 occupations. For gender i might simplx add if
>>>>> fem==0 to the above command. For occupation is there a loop?
>>>>
>>>> I think you asked that question before.
>>>>
>>>> Here are two ways:
>>>>
>>>> *------------ begin example -------------
>>>> sysuse nlsw88, clear
>>>> gen byte black = race == 2 if race < 3
>>>>
>>>> reg wage ibn.black#ibn.occupation, nocons
>>>> table occupation black, c(mean wage)
>>>> *------------- end example ---------------
>>>>
>>>> Hope this helps,
>>>> Maarten
>>>>
>>>>
>>>>
>>>>
>>>> --
>>>> --------------------------
>>>> Maarten L. Buis
>>>> Institut fuer Soziologie
>>>> Universitaet Tuebingen
>>>> Wilhelmstrasse 36
>>>> 72074 Tuebingen
>>>> Germany
>>>>
>>>>
>>>> http://www.maartenbuis.nl
>>>> --------------------------
>>>> *
>>>> *   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/
>>>>
>>>
>>>
>>> --
>>> Chiara Mussida
>>> PhD candidate
>>> Doctoral school of Economic Policy
>>> Catholic University, Piacenza (Italy)
>>> *
>>> *   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/
>>
>>
>>
>> --
>> --------------------------
>> Maarten L. Buis
>> Institut fuer Soziologie
>> Universitaet Tuebingen
>> Wilhelmstrasse 36
>> 72074 Tuebingen
>> Germany
>>
>>
>> http://www.maartenbuis.nl
>> --------------------------
>>
>> *
>> *   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/
>>
>
>
> --
> Chiara Mussida
> PhD candidate
> Doctoral school of Economic Policy
> Catholic University, Piacenza (Italy)
>
> *
> *   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/



-- 
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------

*
*   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