One Step to Efficient Synthetic Data
This addresses the problem of generating reliable synthetic data for researchers and practitioners, offering a method that is both computationally efficient and applicable to parametric models, including for differential privacy, though it builds on existing synthetic data concepts.
The paper tackles the inefficiency and inconsistency of synthetic data generated by sampling from fitted models, proposing a new method that ensures asymptotically efficient summary statistics and convergence to the true distribution, with empirical evidence supporting its effectiveness.
A common approach to synthetic data is to sample from a fitted model. We show that under general assumptions, this approach results in a sample with inefficient estimators and whose joint distribution is inconsistent with the true distribution. Motivated by this, we propose a general method of producing synthetic data, which is widely applicable for parametric models, has asymptotically efficient summary statistics, and is both easily implemented and highly computationally efficient. Our approach allows for the construction of both partially synthetic datasets, which preserve certain summary statistics, as well as fully synthetic data which satisfy the strong guarantee of differential privacy (DP), both with the same asymptotic guarantees. We also provide theoretical and empirical evidence that the distribution from our procedure converges to the true distribution. Besides our focus on synthetic data, our procedure can also be used to perform approximate hypothesis tests in the presence of intractable likelihood functions.