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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Reported significance levels of parameter estimates wrong?


From   Benjamin Niug <benjamin.niug@googlemail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Reported significance levels of parameter estimates wrong?
Date   Wed, 28 Mar 2012 11:17:26 +0200

Hi Maarten,

Thx for clarification. Sorry for underinforming you and spelling Stata
in an inappropriate manner... :-)

Regarding the calculation, I pursued as follows: I calculated the
t-stats by estimate/std.error given by Stata and calculated the
degrees of freedom by N-K (N sample size; K number of regressors).

Number of obs      =      1564
Group variable: country_code;Number of groups   =         4

with 12 indep. variables including the constant. Then I looked up the
(critical) t-values given my degrees of freedom using the student-t
distribution tables available online and then compared...

You see the mistake?

Best,
Benjamin

Am 28. März 2012 11:01 schrieb Maarten Buis <maartenlbuis@gmail.com>:
> --- On Wed, Mar 28, 2012 at 8:53 AM, Benjamin Niug wrote:
>>>> I am estimating a fixed effects regression calculating clustered
>>>> standard errors using the -xtreg var1 var2 var3,fe vce(cluster
>>>> variable) - command.
>>>>
>>>> STATA reports the parameter estimates and their standard errors.
>>>> However, I am suprised that some of the parameter estimates are not
>>>> marked as being signficant - although, when calculating the t-values
>>>> manually, they should be.
>
> ---On Wed, Mar 28, 2012 at 10:47 AM, Benjamin Niug wrote:
>> I am using  the -outreg2- command. In its helpfile it is stated that
>> "(...), the  default symbol(***, **, *). The significance levels of
>> 0.01, 0.05, and 0.10 will be automatically assigned in  that order.
>> (...)"
>
> You should have mentioned that in your first post. How are we supposed
> to know from your original question that you are using -outreg2-? Your
> original question can only be interpreted as you were looking at the
> output of -xtreg-. Moreover, -outreg2- is a user written program, so
> per the Statalist FAQ you must say where you got it from. This is not
> to annoy you, but to help you ask answerable questions. There are
> typically multiple versions of user written software floating around
> in cyber space, and it obviously helps if we are all talking about the
> same piece of software... The final bit of information that is missing
> from your question is how you did the manual computation of the
> t-values/p-values. My guess would be that you made a mistake, but
> since you did not tell us what you did it can only be a guess.
>
> -- Maarten
>
> Ps. Note that it is Stata not 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/

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index