Social science shows a growing interest on multivariate models for discrete variables able to capture even complex pattern of relationships among a collection of observable factors. Chain Graph Models use graphs to illustrate and shape these conditional independence assumptions. Furthermore, the different types of association among variables are well represented through directed and undirected arcs. This visual tool is supported from a set of parameters that capture and describe the association. In this work we use these models to study the poverty status and particularly how this one can be affected from a group of selected variables. Several Chain Graph Models on two different cross-section data sets of Hungarian and German Household were tested. The better one for each data set is deeply studied with a particular attention to the parameters denoting the connection between the variables. From this analysis a strong effect of the considered social variables on the poverty status is highlighted in both data-sets.
Chain Graphical Models- a German and Hungarian Study on Poverty and Social Environment / F. Nicolussi - In: Working paper 16/3[s.l] : Vita e Pensiero, 2016. - ISBN 9788834331972.
|Titolo:||Chain Graphical Models- a German and Hungarian Study on Poverty and Social Environment|
|Parole Chiave:||Marginal Models; Graph Models; Marginal Log-Linear parameters; Income inequality; Welfare system|
|Settore Scientifico Disciplinare:||Settore SECS-S/01 - Statistica|
|Data di pubblicazione:||2016|
|Tipologia:||Book Part (author)|
|Appare nelle tipologie:||03 - Contributo in volume|