As a rule of thumb most researchers claim that n>200. However it depends on the type of research and number of latent variables times (200, 400, 800....3200) divided by pf.

You better check RV Krejcie and DW Morgan, 1970,determining sample size for Research Activities, Educational and Psychological Measurement, 30: 607- 610. another ref, MA Hertzog, Considerations in determining sample size for pilot studies. Res. In Nursing and Health, 2008,31: 180- 191. He suggests a sample over 40 to be enough. Regards.

There is no definitive answer to this question as the minimum sample size for confirmatory factor analysis (CFA) depends on a number of factors, including the number of variables in the model, the complexity of the model, and the desired level of power. However, some general guidelines suggest that a sample size of at least 200 is necessary for CFA, with larger sample sizes being recommended for more complex models.

Here are some specific guidelines for determining the minimum sample size for CFA:

• For models with a small number of variables (e.g., 5-10 variables), a sample size of at least 200 is recommended.
• For models with a moderate number of variables (e.g., 10-15 variables), a sample size of at least 300 is recommended.
• For models with a large number of variables (e.g., 15 or more variables), a sample size of at least 500 is recommended.

Some additional factors that you might want to consider when determining the minimum sample size for CFA:

• The reliability of the measurement variables. If the measurement variables are not reliable, then a larger sample size is required to obtain accurate parameter estimates.
• The amount of missing data. If there is a lot of missing data, then a larger sample size is required to compensate for the missing data.
• The desired level of precision. If a high level of precision is desired, then a larger sample size is required.