I am estimating a nested logit sequentially using clogits. When I calculate
inclusive values from the last step and include these as regressors in the
previous step, all of my other coeffs turn completely insignificant. When I
do not include the inclusive values everything is much different (ie many
significant coeffs). Any ideas why this is happening?
Thanks,
Emla.
_________________________________________________________________
Stay in touch with absent friends - get MSN Messenger
http://www.msn.co.uk/messenger