See update above,

Thom

]]>In my case, I compare three overlapping correlations. The CI of the first one is slightly overlapping with the second, and the second and third are almost the same.

So in principle I am just interested if the first one is higher than the other two. If I perform CI of the difference as described here, I get small bust significant differences (CI ~0.02 -0.09).

To report this result I would just write: There was a significant difference between the correlation of XY and XZ (CI: 0.02-0.09). ? ]]>

http://link.springer.com/article/10.3758/s13428-012-0289-7

https://sites.google.com/a/lakeheadu.ca/bweaver/Home/statistics/spss/my-spss-page/weaver_wuensch

http://core.ecu.edu/psyc/wuenschk/W&W/W&W-SAS.htm

Cheers,

Bruce