[R-meta] Calculate correlation coefficient from (un)standardized regression coefficient

[Wiertsema, M.]

Hi everyone,

I am currently working on a meta-analysis on the longitudinal
association between bullying (predictor) and social status (outcome).
Because most studies used continuous variables for the outcome, we
want to convert all reported effect sizes into a correlation
coefficient.

Here is where the trouble starts:

I want to calculate r from a path estimate (i.e., regression
coefficient), but the only code I can find for this type of converting
uses an argument for sample sizes of two groups (treatment and
control; r package "esc"), whereas 'my' study has no groups and only a
total n. Do you know whether there is  another way to calculate the
correlation coefficient from an (un)standardized regression
coefficient? Also, if yes: is it enough to calculate r with only a
regression coefficient and a total n or is more information needed and
what type of information is then needed to calculate r ?

For example: I have a standardized path estimate between T1 bullying
and T2 popularity of 0.06 and total n of model = 432. Is it at all
possible to convert this into a r coefficient or do I need more
information?

Please let me know if anything is unclear.
Many thanks in advance!

Best,
Maria


-- 
PhD student
University of Groningen, Faculty of Behavioural and Social Sciences
Grote Rozenstraat 38, 9712 TJ Groningen
email: m.wiertsema using rug.nl | phone: 050 - 363 3182