Providing Accurate Models across Private Partitioned Data: Secure Maximum Likelihood Estimation

TL;DR

This paper presents a privacy-preserving method for accurate maximum likelihood estimation across partitioned data sources, enabling analysis without data sharing or revealing true intermediate statistics, and achieving results equivalent to full data analysis under certain conditions.

Contribution

The authors develop a novel approach for secure multivariate normal likelihood estimation across separated datasets that maintains privacy and matches full data results under specific assumptions.

Findings

Method achieves identical estimates as full data analysis under certain assumptions.

Privacy is preserved by adding noise at each data partition.

Software and algorithms are provided for practical implementation.

Abstract

This paper focuses on the privacy paradigm of providing access to researchers to remotely carry out analyses on sensitive data stored behind firewalls. We address the situation where the analysis demands data from multiple physically separate databases which cannot be combined. Motivating this problem are analyses using multiple data sources that currently are only possible through extension work creating a trusted user network. We develop and demonstrate a method for accurate calculation of the multivariate normal likelihood equation, for a set of parameters given the partitioned data, which can then be maximized to obtain estimates. These estimates are achieved without sharing any data or any true intermediate statistics of the data across firewalls. We show that under a certain set of assumptions our method for estimation across these partitions achieves identical results as estimation with the full data. Privacy is maintained by adding noise at each partition. This ensures each party receives noisy statistics, such that the noise cannot be removed until the last step to obtain a single value, the true total log-likelihood. Potential applications include all methods utilizing parameter estimation through maximizing the multivariate normal likelihood equation. We give detailed algorithms, along with available software, and both a real data example and simulations estimating structural equation models (SEMs) with partitioned data.