Disclaimer: English Kinda Thing

The sole purpose of the "English Kinda Thing" is to document my attempts to correct my own mistakes in standard English usage and to share the resources I find. In no way do I attempt to teach nobody English through these blurbs--just as I intend not to teach nobody to be a neurotic and psychotic handicap in Ratology Reloaded or Down with Meds! :-)

Friday, February 24, 2012

Creating a weighted average effect size

The following link gives you an idea about how to calculate the weighted average effect size.

http://effectsizefaq.com/2010/05/30/can-you-show-me-how-to-do-meta-analysis-in-just-2-minutes

Essentially, you need to have information on effect size r and the sample size

Say following is what your data looks like:
For effect size 1: r1=0.72, n1=21
For effect size 2: r2=0.53, n2=43
For effect size 3: r3=0.67, n3=44

The weighted average effect size
=(r1*n1+r2*n2+r3*n3)/(n1+n2+n3)
=(0.72*21+0.53*43+0.67*44)/(21+43+44)
= 67.39/108
=0.623981 (0.62)




Of course you can go up to effect size n and I can put it all the way to the nth except for...


(A nice song to break your from the tiring pursuit towards  a weighted average effect size)
 
At the same time, if you are like me started from Cohen's d, you would have to convert Cohen's d into r.

http://www.uccs.edu/~faculty/lbecker/

While Becker's effect size calculator might come in handy, if you need to do a whole lot of conversions, you might consider simply put all things into excel everything would be spitted out in split second with one paste...

If this case, you would need to understand a secret code on Becker's page...

This question mark hidden inside of a black diamond... apparently indicates..."squart root." 8-O lol


Bon chance.

Let me know shall you have any question.

(Wouldn't love to make the algorithm etc looking for beautiful except for... a bit too tired for the day.  Sorry.)

No comments:

Post a Comment