We propose a latent variable approach for modeling repeated multiple continuous responses. First the item correlation over time is explained by using latent growth curves, then the variability among items is accounted for by an overall latent variable. An EM algorithm is implemented to obtain maximum likelihood estimation of the model parameters
Bianconcini S., Cagnone S. (2010). A multilevel latent variable model for multidimensional longitudinal data. BERLIN : Springer Verlag.
A multilevel latent variable model for multidimensional longitudinal data
BIANCONCINI, SILVIA;CAGNONE, SILVIA
2010
Abstract
We propose a latent variable approach for modeling repeated multiple continuous responses. First the item correlation over time is explained by using latent growth curves, then the variability among items is accounted for by an overall latent variable. An EM algorithm is implemented to obtain maximum likelihood estimation of the model parametersFile in questo prodotto:
Eventuali allegati, non sono esposti
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
