/mcfarland

This is a short tutorial on how to compare latent factor models and psychometric network models using the R package Psychonetrics (Epskamp, 2020).

Primary LanguageR

Readme

We here show how to compare latent factor models and psychometric network models using the R package Psychonetrics (Epskamp, 2019).

The material here accompanies the paper Kan, K.J., de Jonge, H., van der Maas, H.L.J., Levine, S.Z., & Epskamp, S. (2020). How to Compare Latent Factor Models and Psychometric Network Models. Journal of Intelligence.

Our tutorial illustrates how

  • A network can be extracted from the data from one sample and fitted on the data of another sample.
    • in other words, how to test if a given network replicates
  • The fit statistics of that network can be compared with the fit statistics of (various) factor models.

The factor models that are fitted are those that were considered by McFarland (2020):

  • A measurement model
  • A (second order) g model
  • A bifactor model

The data concern WAIS-IV US validation sample data and WAIS-IV Hungary validation sample data.

References

Epskamp, Sacha. 2020b. Psychonetrics: Structural Equation Modeling and Confirmatory Network Analysis. R Package Version 0.7.1.

Kan, K.J., de Jonge, H., van der Maas, H.L.J., Levine, S.Z., & Epskamp, S. (2020). How to Compare Latent Factor Models and Psychometric Network Models. Journal of Intelligence.

McFarland, D. J. (2020). The Effects of Using Partial or Uncorrected Correlation Matrices When Comparing Network and Latent Variable Models. Journal of Intelligence, 8(1), 7.