Dear Nick,
Thanks for the suggestion, however, replacing the 4df quintiles
version of the variable by a 1df linear version results in a different
model. What I want to do is replace it by a set of polynomial
orthogonal dummy variables totalling 4df as can be done in SPSS.
Can you tell me how to do this in STATA?
> N.Steggles
> >
> > I am using the following command on my data set, and now wish to
> > test for linear trend across categories of townquin?
> >
> > xi: logistic trier agey7 i.etnicwh i.townquin, cluster(school)
>
> Presumably you should now think of using not
> i.townquin but townquin in the model.
>
> Nick
> [email protected]
>
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
Dr Naomi Steggles
Research Fellow HABIT study
Health Behaviour Unit
Department of Epidemiology and Public Health
University College London
Brook House
2-16 Torrington Place
London, UK
WC1E 6BT
020 7679 6635
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
