Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: Random coefficients model


From   Lu Zhang <lu.zhang@ualberta.ca>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Random coefficients model
Date   Mon, 3 Jun 2013 11:28:51 -0600

The model I would like to estimate is: V =a+b1*Size+b2*Lev+b3*K, i.e.
firm value is a function of size, leverage and capital. I have an
unbalanced firm-year panel with over 500 firms and 30 years. I would
like b1 and b2 to be fixed across all firms and b3 to be
firm-specific. I agree that -xtrc- wouldn't be able to do this, but I
am not quite sure -xtmixed- is the correct model to use. If allowing
all three coefficients to be random, which one of the two methods
would be a better fit? Thanks a lot.

Cheers,

Lu


On Sat, Jun 1, 2013 at 12:34 PM, Jeph Herrin <stata@spandrel.net> wrote:
> Since you seem to want some coefficients to not be random, then -xtrc- will
> not work for you; the model it estimates assumes all coefficients are
> random.
>
> Other than that, I'm not sure how to advise you. If you explained what model
> you wanted to estimate, it would be easier to identify which Stata command
> you should use.
>
> cheers,
> Jeph
>
>
> On 5/31/2013 4:27 PM, Lu Zhang wrote:
>>
>> Hi Jeph,
>>
>> Thanks for your reply. I found that both xtmixed and xtrc can do
>> random coefficients model in Stata. I have an unbalanced firm-year
>> panel with over 500 firms and about 30-year long time series. I want
>> to calculate a regression coefficient for each firm. I am not sure
>> which one of the two methods fits my data better and what are the
>> difference between them. Any advice?
>>
>> Thanks.
>>
>> Lu
>>
>> On Fri, May 31, 2013 at 2:04 PM, Jeph Herrin <stata@spandrel.net> wrote:
>>>
>>> Yes. Typically, one must specify which coefficients are random; other
>>> remain
>>> fixed.
>>>
>>> I suggest you look at -help xtmixed-.
>>>
>>>
>>> cheers,
>>> Jeph
>>>
>>>
>>>
>>>
>>>
>>> On 5/31/2013 2:40 PM, Lu Zhang wrote:
>>>>
>>>>
>>>> Hi,
>>>>
>>>> I have a question about the random coefficients model. I am wondering
>>>> whether it is possible to fix some of the independent variables, i.e.
>>>> the same coefficients across all the groups, and only allow one of the
>>>> independent variable to have random coefficient, i.e. each group has
>>>> its own coefficient? Any advice or suggestions will be greatly
>>>> appreciated.
>>>>
>>>> Thanks.
>>>>
>>>> Lu
>>>> *
>>>> *   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index