Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: mlogit and IV? polychotomous logistic model and endogenousexplanatory variable

From   Marcello Pagano <>
Subject   Re: st: RE: mlogit and IV? polychotomous logistic model and endogenousexplanatory variable
Date   Mon, 13 Sep 2004 14:10:39 -0400

If it is good enough for the Oxford English Dictionary,
it is good enough for me:

Divided, or involving division, into many
(or more than two) parts, sections, groups, or branches:
= POLYTOMOUS <>. So polychotomy, division into more than two
parts or groups, as in classification: = POLYTOMY <>.

*1858* MAYNE <> /Expos. Lex./, /Polychotomus/, applied to a body that is
divided into numerous articulations..: polychotomous. *
1887* /Amer. Naturalist/ Oct. 915 Polychotomy is probably never more
than provisional, and all classification will eventually be dichotomous.

So until we eventually reach the dichotomy where some of us
are right and some of us are wrong, let's allow polychotomous.


Nick Cox wrote:

My only advice is marginal to your main question.

The term "polychotomous", although common in the literature, is malformed and based on a misparsing of the word "dichotomous", whose elements are "dicho" and "tomous". The term "polytomous", also common in the literature, is more nearly correct.
Help stamp out this linguistic monstrosity!
N.B. this is a different kind of argument from those in favour of "heteroskedasticity" rather than "heteroscedasticity". In the latter case, there are plenty of precedents for rendering the Greek letter
kappa into the English letter c, so one could be sceptical about that argument.
"polychotomous" just got into the literature because someone didn't understand the etymology of "dichotomy" and other people copied that mistake. It's still wrong.
Ngo,PT, a.k.a. Thi Minh

Sorry to bother you again for the second time in the day!

I would like estimate a polychotomous logistic model using mlogit. The main explanatory variable (say X) I use is endogenous and in binary models, I have used IVs using the ivprob command. How would one go about estimating polychotomous logistic model with an endogenous variable for which I have an instrument? I am interested in getting the relative risk ratio as I am trying to differentiate the impact X on the various discrete categories of Y on the left hand side.

Any advice would be really appreciated. It is the first time I am using logit/probit and
polychotomous models.

* For searches and help try:

*   For searches and help try:

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