Family Research Quantitative Methods

This is a great and informative article. Thanks for posting it! While I am in the early stages of my statistical and methodologcal training many of the terms are still new to me...however, reading this article (and others like to to come I hope!) are very helpful for me as I work to "put all the pieces together!"

Thanks, Jane

"It is advisable to test for nonindependence controlling for the predictor variables. This is something that is often not done, but should be."

This was the most helpful line in the link from this post. I like tips like this. I know that at some point tips like this will be tips I am able to give as opposed to only receiving. I hope that there are more to come.

I found the second link on dyadic analysis helpful, especially because I was supposed to read up on intraclass correlations this week! It follows simple ANOVA logic, but the dyad is entered twice in order for computation. Actually, it’s pretty simple:

“ ANOVA Intraclass Correlation

The MSB equals 6.828 and the MSW equals 1.750 making the intraclass correlation equal to

6.828 - 1.750
---------------------- = .592
6.828 + 1.750

The F test equals F(9,10) = 6.828/1.750 = 3.902, p = .046 (two-tailed). Thus, the F test is statistically significant and it is concluded that scores are not independent.�

Out of the readings I’ve done on intraclass correlations so far (both scholarly and websites), this by far explains it the best to me. So far, I understand ANOVA better than regression (even though they are really the same thing), so topic 5 of this website made me at least theoretically understand what an intraclass correlation in how it tests for independence. However, I'm still trying to wrap my head around how to use this in order to compute reliability scores. The following website seems helpful:

http://ourworld.compuserve.com/homepages/jsuebersax/icc.htm

Thanks!