Statalist


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

Re: st: Chi-square test for Categorical Data Analysis


From   Richard Williams <[email protected]>
To   [email protected]
Subject   Re: st: Chi-square test for Categorical Data Analysis
Date   Tue, 18 Sep 2007 18:54:21 -0500

At 04:00 PM 9/18/2007, Maarten buis wrote:
> Second question - does the chi-square test convey any additional
> information other than the fact that the distributions are different?
> That is, since only the number of observations in each group is being
> tested, can I, for example, conclude that Group A is making
> significantly more income than Group B?

No, the Chi-square test just says that these distributions are
different. Again -intreg- will give you more meaningfull output.
Actually, since it is a 2 by 2 table, you can do a z-test with a signed effect. See case II of

http://www.nd.edu/~rwilliam/stats1/Categorical-Stata.pdf

But note: this would just say that one group had significantly more people above the median than the other group did. That isn't necessarily the same as one group making significantly more money. For example, one group might have relatively few people above the median, but those people could be really really really rich. Or, there might be no significant differences in % above the median, but the above average people in one population could be a lot richer than the above average people in the other population.

In the Stata reference manual for intreg, it gives an example along the lines of what Martin later suggests, i.e. log the endpoints of income.


-------------------------------------------
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/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