Hi everyone, I need help in how to determine the small, medium and large sample size for correlation coefficients? is there any reference or journal about that? Thanks in advanced!
You need more data if you would like to prove weak correlation as statistically significant (e.g. corr = 0.20) than if you would like to prove as significant strong correlation (e.g. corr = 0.80).
See https://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#statug_power_sect005.htm for details (if you have SAS software available)
You can use G*Power software to calculate sample size for correlation or any other experiment, G*Power is free to download and easy to use after reading the manual, the download link: