[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: how to deal with categories?

From   Andrea Bennett <>
Subject   Re: st: RE: how to deal with categories?
Date   Tue, 3 Jun 2008 15:21:07 +0200

Dear Martin,
I might have confused you. In the case of "age" I indeed have a continuous variable (which is your point) BUT in the case of income I have income-categories (due to survey structure) and have to deal with that. So, in the case of income categories present, would you think including an interaction dummy for the highest category to be sensible (because the category represents individuals with income>=10'000 USD; not like income>3'000<4'000)?

Many thanks in advance!


On Jun 3, 2008, at 2:56 PM, Martin Weiss wrote:

Regarding 1., it is hard to see why you let dummies eat up your degrees of
freedom when you have a continuous variable "income" which -regress-
accepts. The fact that there is no upper limit for income does not render it
invalid as a covariate. Just include income itself without further ado (pun
intended :-) ).
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index