Modelling Sequences of Events with Chain Graph Models

Marcus Wurzer, Reinhold Hatzinger

Publikation: Beitrag in Buch/KonferenzbandBeitrag in Sammelwerk

Abstract

Graphical Modelling can be seen as a type of multivariate analysis that is of particular usefulness in very complex multivariate systems with complicated structures of dependency. Graphical Models are, as well as Structural Equation Models, an extension of the Path Models introduced by Wright (1921), but in contrast to SEMs, they can also be used to model categorical variables (Wermuth 2003). Additionally, Graphical Models get input from other analysis techniques, including Log-linear Models and Covariance Models, as Whittaker (1990) points out. Furthermore, the principles of independence and conditional independence are important contributors. Darroch, Lauritzen, and Speed (1980) were the first ones to bring together these techniques and principles and showed that Graphical Models are a subset of Log-linear Models that allow - under certain assumptions - a simple interpretation of the underlying dependence structure. Since many modelling tasks in microsimulation involve a high number of potentially influential predictors and/or chains of dependencies between (blocks of) variables, Graphical Models are useful in the sense that they alleviate the task of structuring these multivariate systems.
OriginalspracheEnglisch
Titel des SammelwerksNew Pathways in Microsimulation
Herausgeber*innen Gijs Dekkers, Marcia Keegan and Cathal O'Donoghue
ErscheinungsortSurrey, England
VerlagAshgate
Seiten259 - 270
ISBN (Print)9781409469315
PublikationsstatusVeröffentlicht - 1 Apr. 2014

Zitat