Re: st: Esttab and "too many base levels specified"

[Richard Herron <richard.c.herron@gmail.com>]

OK, I see. You don't have -if- or -in- statements in your -logit-
regressions, but it still could be that missing observations result in
what you've -fvset- as base being omitted from your regression
samples.

Try something like -fvset base last year- before your regressions. You
should do the same for the -lb*- variable (I guess it is represented
by one of the local macros).

"HTH" is an acronym for "hope this helps." Sorry for the short-hand. :-)

On Sun, Oct 14, 2012 at 2:43 PM,  <ma9545@bdvb.de> wrote:
> Hi HTH,
> What do you mean with using statements -if and -in?
> Can you give an example based on my dofile?
> And how can I bind my fvset?
> I didnt find such examples in the handbook..
> Thanks
> Mehmet
>
>
>> Your -fvset- may not be binding. Do you use an -if- or -in- statement
>> that removes your -fvset- from the regression sample?
>>
>> I am most successful using -last- with -fvset-. HTH.
>>
>> On Sun, Oct 14, 2012 at 1:58 PM,  <ma9545@bdvb.de> wrote:
>>> Dear friends, I have a serious problem. Please help me. I'm running a
>>> bunch of regressions, storing the results, and trying to output the
>>> results using esttab. Whenever I run my regressions and include business
>>> or year dummies, esttab gives me the error "too many base levels
>>> specified" (even though the dummies aren't included in the table).
>>> I also used fvset before running the regressions. The regression results
>>> are ok, but how can I put the bunch of results in the esttab output.
>>> Here
>>> is my dofile:
>>>
>>> logit `int' `roe' `basisv' `linecontrols' i.year, cluster(groupid);
>>> eststo;
>>> logit `int' `roa' `basisv' `linecontrols' i.year, custer(groupid);
>>> eststo;
>>>
>>> esttab,
>>> indicate("Line of business controls = lb*" "Year dummy variables =
>>> year*")
>>> se b(3) scalars(N r2_a) label replace varwidth(30) obslast nogaps
>>> align(l)
>>> compress nogap title(title here)
>>> star(* 0.10 ** 0.05 *** 0.01);
>>>
>>> esttab using review_x1.rtf,
>>> indicate("Line of business controls = lb*" "Year dummy variables =
>>> year*")
>>> se b(3) scalars(N r2_a) label replace varwidth(30) obslast nogaps
>>> align(l)
>>> modelwidth(6) nogap title(title here)
>>> star(* 0.10 ** 0.05 *** 0.01);
>>>
>>> eststo clear;
>>>
>>>
>>> Thank you in advance,
>>> Mehmet Altun
>>> *
>>> *   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/