Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: Constant term in Logit regression


From   "JVerkuilen (Gmail)" <[email protected]>
To   [email protected]
Subject   Re: st: Constant term in Logit regression
Date   Sun, 21 Apr 2013 15:05:31 -0500

On Sun, Apr 21, 2013 at 1:15 PM, Athinagoras Konstantinidis
<[email protected]> wrote:
>
> In my logit regression all of my coefficients are significant under
> the 10% s.l. However, the constant term has  a p-value of about 0.600.
> The regression without it has equally good t statistics as before for
> the rest variables.
>
> Can I  permanently remove it from my regression/model with the
> "noconst" option or is it considered a bad thing?

You hardly ever interpret the constant unless it's been scaled to be
interpretable. It just represents the baseline probability of an event
in the given population when the other X variables are equal to 0 and
you should probably control for it. Unless you have created a
meaningful scaling for the X variables what the constant's value is is
arbitrary. Beyond that, it is highly unlikely that you intend to fit a
model with it equal to 0 a priori, so the fact that it is in a
statistical sense is just one of those things.

Jay
*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index