Graduate School and Research Center in Digital Sciences

Assessing Bayesian nonparametric log-linear models: an application to disclosure risk estimation

Carota, Cinzia; Filippone, Maurizio; Polettini, Silvia

Submitted on ArXiV, January 16th, 2018

We present a method for identification of models with good predictive performances in the family of Bayesian log-linear mixed models with Dirichlet process random effects. Such a problem arises in many different applications; here we consider it in the context of disclosure risk estimation, an increasingly relevant issue raised by the increasing demand for data collected under a pledge of confidentiality. Two different criteria are proposed and jointly used via a two-stage selection procedure, in a M-open view. The first stage is devoted to identifying a path of search; then, at the second, a small number of nonparametric models is evaluated through an application-specific score based Bayesian information criterion. We test our method on a variety of contingency tables based on microdata samples from the US Census Bureau and the Italian National Security Administration, treated here as populations, and carefully discuss its features. This leads us to a journey around different forms and sources of bias along which we show that (i) while based on the so called "score+search" paradigm, our method is by construction well protected from the selection-induced bias, and (ii) models with good performances are invariably characterized by an extraordinarily simple structure of fixed effects. The complexity of model selection - a very challenging and difficult task in a strictly parametric context with large and sparse tables - is therefore significantly defused by our approach. An attractive collateral result of our analysis are fruitful new ideas about modeling in small area estimation problems, where interest is in total counts over cells with a small number of observations.

Arxiv Bibtex

Title:Assessing Bayesian nonparametric log-linear models: an application to disclosure risk estimation
Keywords:Bayesian model selection, Disclosure risk, Dirichlet process random effects, Log-linear mixed models, Model?s predictive performance, Selection-induced bias, Small area estimation
Department:Data Science
Eurecom ref:5429
Copyright: © EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Submitted on ArXiV, January 16th, 2018 and is available at :
Bibtex: @inproceedings{EURECOM+5429, year = {2018}, title = {{A}ssessing {B}ayesian nonparametric log-linear models: an application to disclosure risk estimation}, author = {{C}arota, {C}inzia and {F}ilippone, {M}aurizio and {P}olettini, {S}ilvia}, booktitle = {{S}ubmitted on {A}r{X}i{V}, {J}anuary 16th, 2018}, address = {}, month = {01}, url = {} }
See also: