Confirmatory factor analysis (CFA) models observed variables (indicators) as noisy manifestations of underlying latent variables (factors). JASP's CFA is built on lavaan
(lavaan.org; Rosseel, 2012), an R
package for performing structural equation modeling. See Brown (2014) or Kline (2015) for books on the topic of CFA.
In the assignment box, continuous and ordinal variables in your dataset can be assigned to different factors. There is a minimum of one factor, and each factor needs to have at least two indicators. You can add factors by pressing the (+) button and remove factors by pressing the (-) button. You may rename factors by changing the name above the assignment boxes. Either scale or ordinal variables are allowed.
If you use any ordinal variables, the chosen estimator will by default be "DWLS" and the test statistic and fit measures will be scaled and shifted (mean and variance adjusted, see lavaan documentation). Other possible estimators are "WLS" and "ULS". When you use ordinal variables it may make sense to choose robust standard errors.
JASP allows the factors in turn to be indicators of a second-order factor. This can be specified by dragging the factor names to the second-order assignment box. Any factors not assigned as indicators of the second-order factor will be allowed to covary with each other and with the second-order factor, but not with the indicators of the second-order factor.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.