Re: Meta-analyzing dependent correlations

Posted by Ryan on May 27, 2014; 5:20pm
URL: http://spssx-discussion.165.s1.nabble.com/Meta-analyzing-dependent-correlations-tp5726226p5726229.html

Interesting topic, Bruce. This just got me thinking about linear mixed modeling--surprise, surprise! 

Going off on a tangent for a moment (and this is truly a tangent, so forgive me), I'd like to point out that it is possible to appropriately estimate a linear correlation between measurements on two variables from dependent samples using a linear mixed model. In other words, imagine if we collected data on x and y at time 1 from N subjects and then collected data on x and y at time 2 from the same N subjects, and we wanted to estimate the linear correlation between x and y--a linear mixed model could be employed. 

Best,

Ryan

On Tue, May 27, 2014 at 7:26 AM, Bruce Weaver <[hidden email]> wrote:

Here's an article in the latest issue of Behavior Research Methods that may
be of interest to some list members:

Meta-analyzing dependent correlations: An SPSS macro and an R script
Shu Fai Cheung & Darius K.-S. Chan
Behav Res (2014) 46:331–345
DOI 10.3758/s13428-013-0386-2

Those with institutional access can use this link:

http://link.springer.com/article/10.3758/s13428-013-0386-2/fulltext.html?wt_mc=alerts.TOCjournals#Sec13





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Meta-analyzing-dependent-correlations-tp5726226.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD