On Inference for Multivariate Regression Model Based on Synthetic Data Generated under Fixed-Posterior Predictive Sampling

Comparison with Plug-In Sampling

Authors

  • Ricardo Moura Nova University of Lisbon
  • Martin Klein U.S. Census Bureau
  • Carlos A. Coelho Nova University of Lisbon
  • Bimal Sinha U.S. Census Bureau

DOI:

https://doi.org/10.57805/revstat.v15i2.208

Keywords:

finite sample inference, maximum likelihood estimation, pivotal quantity, plug-in sampling, statistical disclosure control, unbiased estimators

Abstract

The authors derive likelihood-based exact inference methods for the multivariate regression model, for singly imputed synthetic data generated via Posterior Predictive Sampling (PPS) and for multiply imputed synthetic data generated via a newly proposed sampling method, which the authors call Fixed-Posterior Predictive Sampling (FPPS). In the single imputation case, our proposed FPPS method concurs with the usual Posterior Predictive Sampling (PPS) method, thus filling the gap in the existing literature where inferential methods are only available for multiple imputation. Simulation studies compare the results obtained with those for the exact test procedures under the Plug-in Sampling method, obtained by the same authors. Measures of privacy are discussed and compared with the measures derived for the Plug-in Sampling method. An application using U.S. 2000 Current Population Survey data is discussed.

Published

2017-04-18

How to Cite

Moura , R., Klein, M., Coelho , C. A., & Sinha, B. (2017). On Inference for Multivariate Regression Model Based on Synthetic Data Generated under Fixed-Posterior Predictive Sampling: Comparison with Plug-In Sampling. REVSTAT-Statistical Journal, 15(2), 155–186. https://doi.org/10.57805/revstat.v15i2.208