I would like to calculate required sample size for my SEM model to achieve the power of at least 0.8.

I read some articles that recommend using Monte-Carlo analysis in order to determine the sample size for the specific model, however cannot find any clear examples of the implementation in R. Ideally, I would like an example considering non-normal data distribution.

Any suggestions on where to find more information on this?


This Github page provides a number of R-based simulation examples for structural equation modeling (sem).

If you are asking for Power Analysis in Model Evaluation, then the syntax is here. However, if you are asking for Power to detect target parameters, then use this syntax.

Furthermore, one of the benefits of the aforementioned github page is that it provides sem codes from popular sem packages, such as Lavaan, simsem, and OpenMx. So there are so many useful things for you to discover here. Personally, I found this page extremely useful for getting your head around sem simulations.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.