Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: RE: RE: AW: -margins- vs -adjust-


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: RE: RE: AW: -margins- vs -adjust-
Date   Wed, 4 Nov 2009 17:29:57 -0000

Let's not go down that route. There are plenty of ways to tackle this
question, and all have advantages and disadvantages. For example,
languages in which you must declare that something is a factor oblige
you to keep converting things when you want to do something else not
deemed consistent with that. 

Stata has chosen one philosophy -- which is roughly that you must tell
Stata what is what on each occasion. 

Once we start with the idea that Stata should be able to figure things
out for itself, then we get into a game in which (for example) you know
something is measured, but it may happen that only two distinct values
are present in the data, so what if Stata jumps to the conclusion that
is really binary (dichotomous), etc.... 

Nick 
n.j.cox@durham.ac.uk 

Jeph Herrin

It seems like -margins- could figure out that -female- is dichotomous.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index