G*power analysis using R

Can anyone help with power analysis. I am new to RStudio, and I have been attempting to do a power analysis using "G*power analysis in R" Thanks much!


It is impossible for any of us to know what it is you're referring to? Is G*power a proprietary software? Is there an R package of it? Do you have data? Please give us a reprex or something (FAQ: How to do a minimal reproducible example ( reprex ) for beginners )

This is Gpower OP is referring to:

There are many R packages that can replicate the GPower capability. For example, the "pwr" package, which has the pwr.t.test() function to perform power calculations for t-tests of means (1-, or 2-sample, etc). To give more specific advice, we would need to know which of the many GPower methods you want to reproduce.

1 Like

Hi Stephen, I am attempting to run an analysis looking at children 12-18 years, and applying variables from another dataset in attempts to see if associations exist. I need to determine alpha, power, and effect size using multivariate analysis. I have consulted with google, and it lists examples such as tcrit, and G * power. I want to use G* power to work out my numbers. I hope I am not being too vague. Thanks so very much.


I think this is less of an RStudio/R issue and more of an issue of what kind of association there is between the variables you're interested in. I know that's not of immediate help to you, but it would be good to grab the closest statistician you can find, sit them down and talk. Lots. The power analysis part of the problem will come after you've decided on an appropriate analysis method. Having said all that, once you've found a suitable analysis method, there will be a power method available, or an approach, that you can use from R, although you might have to do some custom coding.

Good luck!

1 Like

Thanks Stephen. Much appreciated!

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.