So it looks like you're running your multi-mediation model through SmartPLS and thus constructed a PLS-SEM model. For PLS-SEM, the effects of the model are calculated and determined separately as an OLS regression at each path and thus, the recommendation is to run power analyses for those separate paths.

For instance, your System USE variable has three predictor variables (System Quality, Information Quality, and E Service Quality). So, you'd run an OLS regression power analysis with the R^2 with three predictors (as the power analysis is conducted at the structural level) with whatever statistical power and alpha you want to designate. You should do this for every endogenous variable to ensure that your model is sufficiently powered at each path.

I'd recommend using G*Power as it's the most common used tool for power analysis but I'm sure any online power analysis calculator would be sufficient as well.

For more information on power analysis for PLS-SEM, see Chapter 3 of Hair et al. 2011:

https://us.sagepub.com/en-us/nam/a-primer-on-partial-least-squares-structural-equation-modeling-pls-sem/book244583

Link to G*Power software:

https://www.psychologie.hhu.de/arbeitsgruppen/allgemeine-psychologie-und-arbeitspsychologie/gpower

*Note: You could also run a monte carlo simulation as there have been some papers to suggest this in recent years but certainly the individual path power analysis makes things much simpler.

Someone recently alerted me to pwrSEM, an app that may be helpful to you. (I have never used it, so cannot give a firsthand recommendation.) The info I was given included this quote from a published article describing the app:

"This app estimates power by running Monte Carlo simulations based on a model and sample size that the user specifies via a guided, step-by-step point-and-click interface. It accommodates a wide range of structural equation models, requires no experience in conducting simulations, and provides a suite of features that help researchers choose the model features that underlie their power analysis" (Wang & Rhemtulla, 2021).

Wang, Y. A., & Rhemtulla, M. (2021). Power analysis for parameter estimation in structural equation modelling: A discussion and tutorial. Advances in Methods and Practices in Psychological Science, 4(1), 1-17. https://doi.org/10.1177/2515245920918253

Link to PDF: https://journals.sagepub.com/doi/pdf/10.1177/2515245920918253

Link to pwrSEM App: https://yilinandrewang.shinyapps.io/pwrSEM/

HTH.

Hi Marco Antonio. Like others have assumed, I do think too that you are using a Structural Equation Model, with the measure portion included. Hancock and xxxx ( ), recommend as a guideline for determining the sample size required for a SEM analysis, to have at least 5 cases per model parameter (no per variable), and if using the ML estimation method. In some statistical software (e.g., SAS), to estimate sample size, it is needed Power and level of significance. If you have this two (e.g., Power = .0; p=.05. Please be careful to understand the software you are using. In SAS, the sample size obtained is per group. Thus, if you have 2 groups, one needs to duplicate or to give each group the same sample size. I hope this is helpful. Feel free to post if you have further questions.

Sample Size Rule

Sekaran (2013) wrote:

"Roscoe (1975) proposes the following rules of thumb for determining sample size:

1. Sample sizes larger than 30 and less than 500 are appropriate for most research.

2. Where samples are to be broken into sub-samples;(male/females, juniors/seniors, etc.), a minimum sample size of 30 for each category is necessary.

3. In multivariate research (including multiple regression analyses),the sample size should be several times (preferably 10 times or more) as large as the number of variables in the study.

4. For simple experimental research with tight experimental controls (matched pairs, etc.), successful research is possible with samples as small as 10 to 20 in size."

Reference

Sekaran, U., 2003. Research methods for business: A skill building approach. John Wiley & Sons.