Semi-nonparametric methods for detecting latent non-normality: A fusion of latent trait and ordered latent class modeling (original) (raw)

This study evaluates the application of Ordered Latent Class Analysis (OLCA) to detect non-normality in continuous latent variables that explain the covariation between dichotomous item-level responses. Through simulations comparing OLCA with restricted models, the results indicate that the likelihood ratio statistic behaves predictably across various conditions and is effective at identifying non-normality especially in larger sample sizes. Additionally, real data from the National Comorbidity Survey reveals differences in latent trait distributions of major depression between genders.