Bayesian non-parametric generation of fully synthetic multivariate categorical data in the presence of structural zeros

Statistical agencies are increasingly adopting synthetic data methods for disseminating microdata without compromising the privacy of respondents. Crucial to the implementation of these approaches are flexible models, able to capture the nuances of the multivariate structure in the original data. In...

Full description

Saved in:
Bibliographic Details
Published inJournal of the Royal Statistical Society. Series A, Statistics in society Vol. 181; no. 3; pp. 635 - 647
Main Authors Manrique-Vallier, Daniel, Hu, Jingchen
Format Journal Article
LanguageEnglish
Published Oxford Wiley 01.06.2018
Oxford University Press
Subjects
Bayesian analysis
Bayesian non‐parametrics
Bias
Censuses
Complex variables
Contingency tables
Dirichlet process
Disclosure risk
Markov chain Monte Carlo methods
Men
Multiple imputation
Multivariate analysis
Nonparametric statistics
Original Articles
Privacy
Statistical analysis
Statistical methods
Toddlers
Online AccessGet full text
ISSN0964-1998
1467-985X
DOI10.1111/rssa.12352

Cover

More Information
Summary:Statistical agencies are increasingly adopting synthetic data methods for disseminating microdata without compromising the privacy of respondents. Crucial to the implementation of these approaches are flexible models, able to capture the nuances of the multivariate structure in the original data. In the case of multivariate categorical data, preserving this multivariate structure also often involves satisfying constraints in the form of combinations of responses that cannot logically be present in any data set—like married toddlers or pregnant men—also known as structural zeros. Ignoring structural zeros can result in both logically inconsistent synthetic data and biased estimates. Here we propose the use of a Bayesian nonparametric method for generating discrete multivariate synthetic data subject to structural zeros. This method can preserve complex multivariate relationships between variables, can be applied to high dimensional data sets with massive collections of structural zeros, requires minimal tuning from the user and is computationally efficient. We demonstrate our approach by synthesizing an extract of 17 variables from the 2000 US census. Our method produces synthetic samples with high analytic utility and low disclosure risk.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0964-1998
1467-985X
DOI:10.1111/rssa.12352