Bayesian Networks (BNs) are multivariate statistical models satisfying sets of conditional independence statements. Recently, BNs have been applied to ofﬁcial statistics problems. The association structure can be learnt from data by a sequence of independence and conditional independence tests using the PC algorithm. The learning process is based on the assumption of independent and identically distributed observations. This assumption is almost never valid for sample survey data since most of the commonly used survey designs employ stratiﬁcation and/or cluster sampling and/or unequal selection probabilities. Then the design may be not ignorable and it must be taken into account in the learning process. Alternative procedures of Bayesian network structural learning for complex designs are becoming of interest. A PC correction is proposed for taking into account the sampling design complexity. In most cases, the design effects are provided only for the cells and for speciﬁc marginals of the contingency table. In such a situation the ﬁrst-order Rao Scott corrections can be computed for those loglinear models admitting an explicit solution to the likelihood equations. Therefore, we focus on decomposable models and the subset of hierarchical loglinear models, typically used to investigate the association structure in terms of (conditional) independence between categorical variables.
|Titolo:||Bayesian network structural learning for complex survey data|
|Data di pubblicazione:||2014|
|Citazione:||Marella D., Musella F., & Vicard P. (2014). Bayesian network structural learning for complex survey data. In 7th International Conference of the ERCIM (European Research Consortium for Informatics and Mathematics) Working Group on Computational and Methodological Statistics (ERCIM 2014).|
|Appare nelle tipologie:||4.2 Abstract in Atti di convegno|