Analysing Sensitive Data from Dynamically-Generated Overlapping Contingency Tables

Abstract

Contingency tables provide a convenient format to publish summary data from confidential survey and administrative records that capture a wide range of social and economic information. By their nature, contingency tables enable aggregation of potentially sensitive data, limiting disclosure of identifying information. Furthermore, censoring or perturbation can be used to desensitise low cell counts when they arise. However, access to detailed cross-classified tables for research is often restricted by data custodians when too many censored or perturbed cells are required to preserve privacy. In this article, we describe a framework for selecting and combining log-linear models when accessible data is restricted to overlapping marginal contingency tables. The approach is demonstrated through application to housing transition data from the Australian Census Longitudinal Data set provided by the Australian Bureau of Statistics.

Keywords

Count data log-linear model marginal model privacy restriction

References

ABS. 2012. TableBuilder user manual. Technical report, Australia Bureau of Statistics, Canberra, ACT (cat.no 2065.0). Available at: http://www.abs.gov.au/tablebuilder (accessed October 2016).

ABS. 2013. Australian Census Longitudinal Dataset: Methodology and quality assessment – 2080.5 – 2006-11. Technical report, Australia Bureau of Statistics, Canberra, ACT. Available at: https://www.abs.gov.au/AUSSTATS/abs@.nsf/Lookup/2080.5Main+Features12006-2016 (accessed October 2016).

Agresti, A. 1981. “Measures of nominal-ordinal association.” Journal of the American Statistical Association 76(375): 524–529. DOI: https://doi.org/10.1080/01621459.1981.10477679.

Agresti, A. 2002. Categorical Data Analysis. Springer, second edition.

Akaike, H. 1974. “A new look at the statistical model identification.” IEEE Transactions on Automatic Control 19(6): 716–723. DOI: https://doi.org/10.1109/TAC.1974.1100705.

Allison, P.D. 1980. “Analyzing collapsed contingency tables without actually collapsing.” American Sociological Review 45(1): 123–130. DOI: https://doi.org/10.2307/2095247.

Bergsma, W., M.A. Croon, and J.A. Hagenaars. 2009. Marginal models: For dependent, clustered, and longitudinal categorical data. Springer Science & Business Media.

Bergsma, W.P. and T. Rudas. 2002. “Marginal models for categorical data.” Annals of Statistics 30(1): 140–159. DOI: https://doi.org/10.1214/aos/1015362188.

Birch, M. 1963. “Maximum likelihood in three-way contingency tables.” Journal of the Royal Statistical Society. Series B (Methodological) 25: 220–233. Available at: https://www.jstor.org/stable/2984562 (accessed November 2017).

10.

Bishop, Y., S. Fienberg, and P. Holland. 1975. Discrete multivariate analysis: Theory and practice. The MIT Press, Cambridge, Massachusetts.

11.

Cameron, A. and P. Trivedi. 1998. Regression analysis of count data. Cambridge University Press.

12.

Chipperfield, J., D. Gow, and B. Loong. 2016. “The Australian Bureau of Statistics and releasing frequency tables via a remote server.” Statistical Journal of the IAOS 32(1): 53–64. DOI: https://doi.org/10.3233/SJI-160969.

13.

Chipperfield, J., J. Brown, and N. Watson. 2017. “The Australian Census Longitudinal Dataset: using record linkage to create a longitudinal sample from a series of cross-sections.” Australian and New Zealand Journal of Statistics 59(1): 1–16. DOI: https://doi.org/10.1111/anzs.12177.

14.

Dahinden, C., M. Kalisch, and P. Bühlmann. 2010. “Decomposition and model selection for large contingency tables.” Biometrical Journal 52(2): 233–252. DOI: https://doi.org/10.1002/bimj.200900083.

15.

Darroch, J.N., S.L. Lauritzen, and T.P. Speed. 1980. “Markov fields and log-linear interaction models for contingency tables.” The Annals of Statistics 8(3): 522–539. DOI: https://doi.org/10.1214/aos/1176345006.

16.

Domingo-Ferrer, J. and J. Mateo-Sanz. 1999. “Resampling for statistical confidentiality in contingency tables.” Computers & Mathematics with Applications 38(11–12): 13–32. DOI: https://doi.org/10.1016/S0898-1221(99)00281-3.

17.

Duncan, G., M. Elliot, and J.-J. Salazar-González. 2011. Statistical Confidentiality: Principles and Practice. Statistics for Social and Behavioral Sciences. Springer, New York, NY, second edition.

18.

Frydenberg, M. 1990. “Marginalization and collapsibility in graphical interaction models.” The Annals of Statistics 8(2): 790–805. DOI: https://doi.org/10.1214/aos/1176347626.

19.

Frydenberg, M. and S.L. Lauritzen. 1989. Decomposition of maximum likelihood in mixed graphical interaction models. Biometrika 76(3): 539–555. DOI: https://doi.org/10.2307/2336119.

20.

Jones, E. and V. Didelez. 2017. “Thinning a triangulation of a Bayesian network or undirected graph to create a minimal triangulation.” International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 25(3): 349–366. DOI: https://doi.org/10.1142/S0218488517500143.

21.

Lang, J.B. 1996. “On the comparison of multinomial and Poisson log-linear models.” Journal of the Royal Statistical Society. Series B (Methodological) 58(1): 253–266. Available at: https://www.jstor.org/stable/2346177 (accessed October 2017).

22.

Lauritzen, S.L. 1996. Graphical models, volume 17. Clarendon Press.

23.

Lee, J.Y., J.J. Brown, and L.M. Ryan. 2017. “Sufficiency revisited: Rethinking statistical algorithms in the big data era.” The American Statistician 71(3): 202–208. DOI: https://doi.org/10.1080/00031305.2016.1255659.

24.

Leimer, H.-G. 1993. “Optimal decomposition by clique separators.” Discrete mathematics 113(1–3): 99–123. DOI: https://doi.org/10.1016/0012-365X(93)90510-Z.

25.

Nelder, J. and R. Wedderburn. 1972. “Generalized linear models.” Journal of the Royal Statistical Society. Series A (General) 135(3): 370–384. DOI: https://doi.org/10.2307/2344614.

26.

Olesen, K.G. and A.L. Madsen. 2002. “Maximal prime subgraph decomposition of Bayesian networks.” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 32(1): 21–31. DOI: https://doi.org/10.1109/3477.979956.

27.

R Core Team. 2016. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. 2016. Available at: https://www.R-project.org/ (accessed November 2018).

28.

Rose, D.J., R.E. Tarjan, and G.S. Lueker. 1976. “Algorithmic aspects of vertex elimination on graphs.” SIAM Journal on computing 5(2): 266–283. DOI: https://doi.org/10.1137/0205021.

29.

Spallek, M., M. Haynes, and A. Jones. 2014. “Holistic housing pathways for Australian families through the childbearing years.” Longitudinal and Life Course Studies 5(2): 205–226. DOI: https://doi.org/10.14301/llcs.v5i2.276.