Hello,
Just testing the water, but I have a query as follows:
Regardless of the strategy adopted for logistic regression modelling, does
anyone have learned opinions about converting continuous variables into
discrete ordinal variables if in continuous form, they are not significant
predictors?
My question pertains to the legitimacy of this and the stage in the
modelling procedure at which this should be done.
Any suggestions would be gratefully received.
thank you
----------------------------------------------------------------------------
David Oatway
Centre for Land Use and Water Resources Research
Porter Building
University of Newcastle
Newcastle upon Tyne
NE1 7RU
United Kingdom
Tel: +44 191 222 5956
Fax: +44 191 222 6563
URL: http://www.cluwrr.ncl.ac.uk
----------------------------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|