This question is sometimes answered in terms of the number of observations times the number of parameters in your model (i.e., the total number of loadings and causal paths). A frequent recommendation is that your sample size should be 10 times the number of parameters.

Hi Dinesh,

I guess you approaching the limit of questions that should be asked on research gate ;)

The sample size requirements cannot be generalized and depend on the model size, and complexity. The best solution would be to run a Monte-Carlo-Simulation which is no rocket science these days (and can be easily done with R).

All the best

Holger

Beaujean, A. A. (2014). Sample size determination for regression models using Monte Carlo methods in R. Practical Assessment, Research & Evaluation, 19(12), 1-16.

Thoemmes, F., MacKinnon, D. P., & Reiser, M. R. (2010). Power analysis for complex mediational designs using Monte Carlo methods. Structural Equation Modeling, 17(3), 510-534.

Wang, Y. A., & Rhemtulla, M. (2021). Power analysis for parameter estimation in structural equation modeling: A discussion and tutorial. Advances in Methods and Practices in Psychological Science, 4(1), 2515245920918253.