Statalist


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

Re: st: income classes as dependent variable


From   Richard Williams <Richard.A.Williams.5@ND.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: income classes as dependent variable
Date   Thu, 11 Dec 2008 09:30:25 -0500

At 08:43 AM 12/11/2008, marcel spijkerman wrote:
Dear Stata users,


My data set contains data on income and a number of characteristics (age, education etc.). I want to explain individual income by the characteristics. Income is not known exactly, it is only known to which income class an individual belongs to. I have reasons to believe that income is not normaly distributed. Can I simply use an ordered logit/probit model or should I use another type of model. and if so, do there exist stata modules to estimate such model.

As Martin suggests, -intreg- may be worth checking into. Note, however, that -intreg- assumes the DV is normally distributed. But check the example the manual gives for -intreg-. It notes that you can log income, and illustrates how you can choose between intreg and oprobit. When it is legitimate to use it, I think intreg is greatly preferable to oprobit, but my understanding is that intreg is very sensitive to violations of its assumptions.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   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