st: Generalized Eta Squared Statistics - Confidence Intervals

[Walter Bischof <wfb@ualberta.ca>]

In a mixed Anova design with a between-subjects factor and a
within-subjects factor, I want to compare effect sizes between the
factors. According to Olejnik & Algina (2003), Bakeman (2005),  and
Richardson (2011), partial eta squared is inappropriate for such cases
(see e.g. Richardson, p. 142), and the generalized eta squared is more
appropriate.

I have no problems manually computing the generalized eta squared from
the Anova table (using, e.g. Bakeman, Table 1), but I have no clue how
to go about determining the confidence intervals. Do you know of an
appropriate source that explains this, or do you even know of a Stata
ado file for doing this?

The "estat esize" command does not compute the generalized eta squared.

Thank you.
Walter

Bakeman, R. (2005). Recommended effect size statistics for repeated
measures designs. Behavior Research Methods, 37(3), 379-384.

Olejnik, S. and Algina, J. (2003). Generalized eta and omega squared
statistics: Measures of effect size for some common research designs.
Psychological Methods, 8(4), 434-447.

Richardson, J.T.E. (2011). Eta squared and partial eta squared as
measures of effect size in educational research. Educational Research
Reviews, 6, 135-147.

-- 
Walter F. Bischof                                E-mail: wfb@ualberta.ca
Department of Computing Science       WWW: http://www.cs.ualberta.ca/~wfb
University of Alberta                           Tel: +1 780 492 3114
Edmonton, T6G 2E9, Canada              Fax: +1 780 492 1071
*
*   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/