[Forum SIS] Avviso di seminario

[Francesca De Battisti]

<signatureafterquotedtext>
</signatureafterquotedtext>


Martedì5 giugno alle ore 12.30, pressol’aula seminari del Dipartimento di Economia, Management e Metodi Quantitatividell’Università degli Studi di Milano (II piano, entrata da via Conservatorio,n. 7), FedericaNicolussi (Università degli Studi di Milano ) terrà un seminario dal titolo: 

  

“STRATIFIEDREGRESSION CHAIN GRAPH MODELS: A STUDY OF (IN)DEPENDENCE RELATIONSHIPS AMONGCATEGORICAL AND ORDINAL VARIABLES” 

  

Abstract   

The relationships among a set of categorical and ordinal variablescollected in a contingency table is deepen studied under different point ofviews. Here we want to take into account the different (in)dependencerelationships that can occur. In particular, beyond the marginal andconditional independencies, the so-called context specific independencies areinvestigated. These last are conditional independencies that hold only for asubset of modalities of the conditioning variables. 

The Hierarchical Multinomial Marginal models, (Bartolucci et al., 2007)seem to give an appropriate parametrization to describe the regressionparameters. We take advantage from these models and provide several originalresults about the representation of context-specific independencies throughRegression Chain Graphical models (Marchetti et al., 2011). In order to capturealso the context specific independencies, we improve the used graphs withso-called ”stratum”, labelled arcs which denoted the context-specificindependencies. The main original results are showed in an application on thereal dataset.  

  

Tutti gli interessati sono invitati a partecipare.  







 
***********************************************************
Francesca De Battisti
Dipartimento di Economia, Management e Metodi Quantitativi 
(III piano, studio n. 29)
Via Conservatorio 7
20122 - Milano
Tel: 02.50321464
Fax: 02.50321505
***********************************************************


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20180530/96136950/attachment-0001.html>