Statistical regularisation techniques have been recently proposed to investigate the structure of sociological measurement scales and psychometric tests. In this context, we propose a Bayesian estimation procedure able to simultaneously estimate the number of latent traits and induce sparsity in the factorial solution.
Unveiling Latent Structures: exploring Multidimensional IRT Models using Dirichlet Process Mixtures
Pasquale Valentini;Lara Fontanella
2023-01-01
Abstract
Statistical regularisation techniques have been recently proposed to investigate the structure of sociological measurement scales and psychometric tests. In this context, we propose a Bayesian estimation procedure able to simultaneously estimate the number of latent traits and induce sparsity in the factorial solution.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
