Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Fixed effects using binary numbers + F test for Fixed effects


From   "joelle farajallah" <joelle.farajallah@hec.ca>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Fixed effects using binary numbers + F test for Fixed effects
Date   Fri, 2 Nov 2007 14:21:39 -0400 (EDT)

Thanks a lot for your answer,
Yes i will restate it clearly :

The model is the following:
 lcrmrteit = â0 + â1 lprbarrit + â2 lprbconvit +d04 + d05 + uit.

lcrmrteit is the log of the crime rate
lprbarrit is the log of the 'probability' of arrest
prbconvit is the 'probability' of conviction
d04 =1 if year == 2004
d05 =1 if year == 2005


The first question is to develop a model with fixed effects using binary
variables that can be estimated by OLS (it is MCO in French) and estimate
this model using Stata

The second question is to use an F test to validate the usage of fixed
effects (restricted F test)

Third question is to estimate the model using the fixed effects and use an
F statistic to validate the presence or absence of fixed effects ( using
integrated commands ?? )

And they finally ask us what the difference is between the 3 F statistics
obtained in these 3 questions , which for me kind of all seem to be the
same.
Thanks in advance for your help.





> What does "fixed effects using binary" mean?  What are d04 and d05? By
> MCO do you mean "Monte Carlo Optimization" to estimate numerical
> integration via sampling?
> 
> The test that all FE are 0, or var(u_i)=0, is reported by -xtreg, fe-
> as a matter of course, I believe, and available as e(F_f) after
> estimation.
> 
> Can you restate your problem in terms of available data, e.g. start with
>    webuse grunfeld, clear
> or the like?
> 
> On 11/1/07, joelle farajallah <joelle.farajallah@hec.ca> wrote:
>> Hi everyone
>> I have quite a few questions about the fixed effects that might sound
>> very
>> beginner level things but i'm getting really stuck with them
>>
>> We have a certain model
>> lcrmrteit = â0 + â1 lprbarrit + â2 lprbconvit +d04 + d05 + uit.
>>
>> The first question is to develop a model with fixed effects using binary
>> that can be estimated by MCO and estimate this model using Stata
>>
>> The second question is to use an F test to validate the usage of fixed
>> effects (restricted F test)
>> Third question is to estimate the model using the fixed effects and use
>> an
>> F statistic to validate the presence or absence of fixed effects ( using
>> integrated commands ?? )
>>
>> And they finally ask us what the difference is between the 3 F
>> statistics
>> obtained in these 3 questions , which for me kind of all seem to be the
>> same.
>> Thanks in advance for your help.
>>
>>
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/support/faqs/res/findit.html
>> *   http://www.stata.com/support/statalist/faq
>> *   http://www.ats.ucla.edu/stat/stata/
>>
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
> 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index