Lorant Vincent asked:
> Which test is able to detect non linearity between a binary dependent
> and continous independent variable ?
If the dependent variable takes both values the function is nonlinear.
Has to be; the only linear functions R --> {0,1} are constant. But I presume
that is not what you meant by "linear"...
> Is using a logistic regression and considering the coefficient of a
squared
> independent variable in the equation sufficient ?
If it's what you mean by linear (and it sounds good to me), then more or
less yes. Caveat: if you have a natural "midpoint" for your X, then
alternatives to linearity that lie completely within the space of odd
functions P = ax + cx^3 + .... might be plausible, and such values would
*not* take the bait if offered an even term bx^2. You might want to see if
the model would come out of its hole if offered a cubic term, as well.
-Robert Dawson
===========================================================================
This list is open to everyone. Occasionally, less thoughtful
people send inappropriate messages. Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.
For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===========================================================================
