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: xttobit & stata 12: Initial values not feasible


From   Surender Komera <surenderraogp@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: xttobit & stata 12: Initial values not feasible
Date   Tue, 3 Jul 2012 21:37:09 +0530

Ok. I'm not sure i got it completely what you are saying. As you see i
don't have any binary variable or any time invariant one as
explanatory variables. All my explanatory variables are ratios and
they are continuous. I didn't clearly get it how i can center them? My
dataset is unbalanced panel of 28800 firm years covering 20 years. I'm
not sure how can go about it. I appreciate if you can site some source
for reading to understand it clearly. However, do you think it can
potentially offer some solution to my problem of "Initial values not
feasible". I appreciate your patience and time.

Thanks - Surender



On Tue, Jul 3, 2012 at 7:27 PM, Maarten Buis <maartenlbuis@gmail.com> wrote:
> On Tue, Jul 3, 2012 at 3:39 PM, Surender Komera wrote:
>> I have not centered explanatory variables (x variables). How can i do
>> that? It will be really helpful if you can explain.
>
> Say you have year of birth, than you would not want to enter it as is
> in a random effects model. A lot of the (random) action in random
> effects models is in the constant, and if you entered year of birth as
> is than that would (typically) be a huge extrapolation, i.e. it would
> refer to people born in the year 0. Say you want to center at 1950,
> than you just create a new variable which contained the year of birth
> - 1950. You can pick any number that is meaningful as long as it is
> within (or close to) the range of your data. This is something you
> only want to do to your continuous explanatory variables, not your
> dependent variable an not to any of the indicator (dummy) variables.
>
> -- Maarten
>
> --------------------------
> 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