Deborah,
Generally, the type of variables examined affects the statistical procedures
that you can employ. When you have two interval(continuous variables), a
Pearson's correlation coefficient (r) is used to measure the strength of the
association between the two variables.
The statistic" eta" is designed for the case when one one of the measures is
nominal and the other is interval. If it is significant, then the two variables
are not independent.
For in depth explanation go to http://www2.chass.ncsu.edu/garson/pa765/eta.htm
and
http://web.uccs.edu/lbecker/SPSS/ctabs1.htm
Tamara
Quoting Deborah Garvey <[email protected]>:
> Greetings.
>
> Please pardon this more general statistical question, although it has a
> STATA component.
>
> I'm reading a paper in the soc literature by Portes & MacLeod (
> "Educating the Second Generation: Determinants of Academic Achievement
> among Children of Immigrants in the United States"
> Journal of Ethnic and Migration Studies, 1999).
>
> Before conducting multivariate analyses, the authors present measures
> of bivariate associations (which economists rarely do). They compare
> mean values of various predictors (e.g., English ability) by national
> origin groups and show eta values for each variable. Eta ranges from
> 0.04 to 0.41.
>
> 1. What is the "coefficient of strength of association"? What exactly
> does eta measure?
>
> 2. They state "all intergroup differences (except sex) are significant
> at the 0.001 level." Does this mean all possible intergroup differences
> (C6,2)? Group differences from the sample mean?
>
> 3. How is eta calculated in STATA?
>
> Thanks. Appreciate your help.
>
> Deb
>
> ******************************
> Deborah Garvey, Ph.D.
> Department of Economics
> Kenna Hall
> Santa Clara University
> Santa Clara, CA 95053
> 408/554-5580
> 408/554-2331 (FAX)
> [email protected]
> http://lsb.scu.edu/~dgarvey
> **********************************
> *
> * 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/
>
*
* 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/
