Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Supported by

Confirmatory Factor Analysis (CFA) Error Message

Hi,

I am trying to conduct a confirmatory factor analysis in JASP. I need to assess a 5 factor model each factor with 4 items. I collected data from 400 participants with two conditions (control and experimental).

However, when I am adding in my factors and add in the items for the 3rd factor onwards I get the following error message:

The model is not admissible: lavaan WARNING: covariance matrix of latent variables

                is not positive definite;

                use lavInspect(fit, "cov.lv") to investigate.

I was just wondering if anyone has had any experience with this and could shed some light or help out.


Thank you!

Chelsea

Comments

  • Hi,

    The error message you encountered in JASP while conducting confirmatory factor analysis (CFA) using lavaan is related to the covariance matrix of the latent variables. This error typically occurs when the covariance matrix is not positive definite, which means it violates the assumptions of the CFA model.

    A positive definite covariance matrix is essential for the model to be estimated correctly, as it ensures that the relationships between the latent variables and their indicators are well-defined. When the covariance matrix is not positive definite, it indicates that there might be issues with the data or the specified model.

    Use in R lavInspect(fit, "cov.lv") to investigate

    🚩

Sign In or Register to comment.