[Forum SIS] seminario Dott. Alessio Farcomeni

[Giorgio Vittadini]

Con preghiera didiffusione

Giorgio Vittadini




>********************************************************
>Dipartimento di Statistica e Metodi Quantitativi
>Via Bicocca degli Arcimboldi, 8 - 20126  Milano
>
>*********************************************************
>
>GENERALIZED LINEAR MIXED LATENT MARKOV MODELS 
>WITH TIME-VARYING RANDOM EFFECTS"
>
>Dott. Alessio Farcomeni
>Universita' di Roma - La Sapienza  - 
>Dipartimento Sanità  pubblica e  Malattie infettive
>
>Venerdì   22 Novembre ore 14.30  aula seminari  4026
>
>
>__________________________________________________________
>
>Abstract:
>Latent Markov models (LM) can be seen as a flexible
>device for taking into account time-varying subject-specific
>unobserved heterogeneity. In the basic LM,
>a random intercept is flexibly allowed to evolve over time.
>The available formulations of mixed LM often assume that any
>additional random effect is time constant.
>The few exceptions are mostly limited to simple specific cases.
>In this work we formulate a mixed latent Markov model in
>which all random effects may freely evolve over time.
>We then generalize our proposal to a block random model
>in which groups of random effects may share some or all
>aspects of their random distribution. We discuss
>the substantial advantages of the latter formulation.
>We show that parameter estimation can be carried out
>with a simple expectation maximization strategy, analogous
>to that used for the basic latent Markov model,
>after an adaptation of the usual forward backward
>recursions and a parsimonious representation
>of the expected complete likelihood.
>Standard errors are derived using Oakes' identity.
>We illustrate with an original application
>to the relationship between health literacy
>and depression in a panel of adolescents.
>In this example subjects are clustered in schools,
>which yields an high-dimensional multivariate time-varying random effect.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20131107/a39b1033/attachment.html>