Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: gologit2
From
Richard Williams <[email protected]>
To
[email protected], "[email protected]" <[email protected]>
Subject
Re: st: gologit2
Date
Wed, 28 Aug 2013 22:37:05 -0500
Multi-equation methods like mlogit and gologit can estimate a lot of
parameters, hence things like extreme collinearity may cause more
grief for them than they do for simpler methods. Having said that,
multicollinearity is not inherently fatal; you might have problems
with a small data set and no problems at all if you have 100,000 cases.
I agree with Maarten that you should examine why the multic exists.
Maybe you have done something stupid, like include a scale along with
the items used to compute the scale. Conversely, if you have a bunch
of items that all measure the same concept, you may be able to create
a single scale out of them that solves your problems.
For more ideas on causes/consequences/possible ways of dealing with
multicollinearity, see
http://www3.nd.edu/~rwilliam/xsoc63993/l11.pdf
At 08:51 AM 8/28/2013, lan zhang wrote:
Good morning!
i want to conduct a gologit2 model, however, the correlations
between my independent variables are very high, almost 0.9. Is it
still possible for me to use the gologit2 model?
thanks
lan
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/