Statalist The Stata Listserver


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

st: MULTICOLLINEARITY


From   "Ojakaa David" <[email protected]>
To   <[email protected]>
Subject   st: MULTICOLLINEARITY
Date   Thu, 21 Jun 2007 09:05:05 -0400

Hello All,

 

 

I have a problem of collinearity in my data. One of my binary variables (Nairobi) in a set of four regional variables (Nairobi, Other urban, Central rural, Other rural) is dropped. Thus, when I run: 

 

 

xi: mlogit cuse i.age1525 i.age2630 i.age3135 . . . . . i.Nrb i.Oturb i.Centrur i.Othrur [pweight=wv005], cl(v001) basecat(3)        

outreg using test.doc, coefastr 

 

I get the response: 

(sum of wgt is   1.8791e+03)

note: _INrb_1 dropped due to  collinearity. 

 

But I do not want this variable to be dropped; instead I exclude the variable for other rural areas from the final regression. My reasoning is that other rural areas would in any case be negatively associated with my outcome variable (which I confirmed).  

 

So I seek your assistance: 

1. Am I right?

2. What other options do I have to do it right? For example, I notice that when I include the command "noconst", all the variables are included and none is omitted due to collinearity. Is this recommended?

 

Thx. 


*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index