The sample size is around 250,000 and number of fixed effects varies
from less than 150 to about 59,000 depending on specification. It's
interesting that this happens once I split the sample into two: one
with less than 200,000 obs and the other with less than 50,000 obs.
Another sample split yields a similar number.
On Sat, Oct 10, 2009 at 12:36 AM, Stas Kolenikov <[email protected]> wrote:
> Something is perfectly correlated with those fixed effects. How large
> is your sample, and how large are your panels?
>
> On Fri, Oct 9, 2009 at 4:32 PM, Sue <[email protected]> wrote:
>> Dear Statalisters,
>>
>> I searched for a similar problem but couldn't find anything. After
>> splitting the sample into two, I run 4 sets of regressions with the
>> same regressors, just adding different fixed effects. Depending on the
>> dependent variable, between 1-3 out of the 4 regressions report the
>> coefficients but not the standard errors(they are reported as (.) ). I
>> use the -areg- command. Any thoughts on what might be causing this?
>> There was no such problem before I split the sample. I'd appreciate
>> your input.
>> *
>> * 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/
>>
>
>
>
> --
> Stas Kolenikov, also found at http://stas.kolenikov.name
> Small print: I use this email account for mailing lists only.
>
> *
> * 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/
