A sample size of 200 is sometimes mentioned as a rule of thumb. As your sample size diminishes you lose statistical power to reject the model. 

The appropriateness of the sample size for SEM is oftentimes assessed in terms of an N:q heuristic (N - an effective sample size, q - independent parameters for estimation). Bentler and Chou’s (1987) recommendation is of a 5:1, but others suggested higher values of e.g. 10:1. Hope this helps. Good luck with your research.

Dear Najmul Hoda,

The issue of sample size in SEM is complicated. It is related to power, bias, and Solution Propriety among many other factors. I would suggest reading the following recent article. It may open the gate for you.

http://journals.sagepub.com/doi/abs/10.1177/0013164413495237

Hi Najmul

at less of simple size for using analysis by SEM is 200 .

hope this Helps

Dear Hoda

A.The sufficient sample size is n >200, please refer to,

http://www.statisticssolutions.com/confirmatory-factor-analysis/).

B. Several references studied related problems of SEM. Some of which are given below:

1. Donna L. Schminkey Timo von Oertzen Linda Bullock(2016). Handling Missing Data With Multilevel Structural Equation Modeling and Full Information Maximum Likelihood Techniques. https://doi.org/10.1002/nur.21724.

Volume39, Issue4, 286-297. https://onlinelibrary.wiley.com/doi/full/10.1002/nur.21724

2. Data Analysis: Structure Equation Modeling (SEM)

January 2016, DOI: 10.1007/978-981-10-0053-9_4. In book: Expatriate Manager’s Adaption and Knowledge Acquisition.

https://www.researchgate.net/publication/301256051_Data_Analysis_Structure_Equation_Modeling_SEM

3. Rufus Lynn Carter (2006). Solutions for Missing Data in Structural Equation Modeling. Research & Practice in Assessment, Volume One: Winter 2006, 1-7,

https://files.eric.ed.gov/fulltext/EJ1062693.pdf

4. Paul D. Allison (2003). Missing Data Techniques for Structural Equation Modeling. Journal of Abnormal Psychology, Vol. 112, No. 4, 545–557.

https://statisticalhorizons.com/wp-content/uploads/Allison-2003-JAP-Special-Issue.pdf

Regards,

Zuhair

There are many opinions on minimal sample sizes in SEM (10 cases per parameter estimated, greater than 300, statistical power of the RMSEA test). And since SEM is a combination of SEM and regression some of these come from those other analyses. If you do not meet the requirement then you can still run the SEM but beware of the limitations of drawing confident conclusions from it. There are some other options. e.g., If you have no latent variables, the sample sizes needed are reduced a lot so consider using only observed variables.