Lucia Coppola, Marco Di Zio, Orietta Luzi, Alessandra Ponti, Mauro Scanu
ISTAT,
via Cesare Balbo 14, 00184 Roma
Italy
e-mail: luzi@istat.it
Bayesian Networks are particularly useful for dealing with high dimensional statistical problems (Jensen, 1996). They allow reducing the complexity of the inspected phenomenon by representing joint relationships among a set of variables, through conditional relationships among subsets of these variables. Roughly, it is equivalent to split the overall problem in many sub-problems, but assuring that the combination of all the single sub-solutions (corresponding to the single sub-problems) will give the optimal global solution. Official Statistics is a natural application field for this technique because of the complexity of statistical surveys carried on in this context. In particular, following Thibaudeau and Winkler (2001), we used the Bayesian Networks for imputing missing values. We performed a first experiment on a subset of anonymous individual records and variables surveyed in 1991 U.K Population Census (SARS).
References
Jensen F. V. (1996) An introduction to Bayesian Networks, Springer Verlag, New York.
Thibaudeau Y., Winkler W.E. (2001) Bayesian networks representations, generalized imputation, and synthetic micro-data satisfying analytic constraints, unpublished manuscript.