Bookmark and Share

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

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

Re: st: what does mean by log likelihood value

From   Maarten Buis <>
Subject   Re: st: what does mean by log likelihood value
Date   Fri, 12 Aug 2011 11:37:39 +0200

On Fri, Aug 12, 2011 at 11:17 AM, dk wrote:
> I just want to know what does it mean by the log likelihood value,
> take a example i have  log likelihood  = - 12.03 in one model and in
> other = 322.003. what actually this values mean.. these values are
> from different examples. In both the examples the model fits to the
> data. I want to know what these values mean.

For discrete models it is the log of the probability of observing the
data that has been observed given the model. For continuous models it
is the related sum of the log densities.

You must be very careful when comparing log likelihoods: Both the
sample and the dependent variable must be exactly the same otherwise
the comparison is completely meaningless.

Also see: <>

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen

*   For searches and help try:

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