Variance-Optimal Offline and Streaming Stratified Random Sampling

TL;DR

This paper introduces VOILA, a variance-optimal offline stratified sampling method that handles bounded strata, and S-VOILA, a streaming algorithm that approximates this optimal allocation with minimal variance increase.

Contribution

It proposes the first variance-optimal offline stratified sampling method for bounded strata and a streaming algorithm that closely approximates this optimal allocation.

Findings

VOILA achieves 1.4 to 50 times lower variance than Neyman allocation.

S-VOILA's variance is typically close to the offline optimal VOILA.

Theoretical lower bound shows any streaming algorithm must have at least an Omega(r) factor worse variance.

Abstract

Stratified random sampling (SRS) is a fundamental sampling technique that provides accurate estimates for aggregate queries using a small size sample, and has been used widely for approximate query processing. A key question in SRS is how to partition a target sample size among different strata. While Neyman allocation provides a solution that minimizes the variance of an estimate using this sample, it works under the assumption that each stratum is abundant, i.e., has a large number of data points to choose from. This assumption may not hold in general: one or more strata may be bounded, and may not contain a large number of data points, even though the total data size may be large. We first present VOILA, an offline method for allocating sample sizes to strata in a variance-optimal manner, even for the case when one or more strata may be bounded. We next consider SRS on streaming data that are continuously arriving. We show a lower bound, that any streaming algorithm for SRS must have (in the worst case) a variance that is {\Omega}(r) factor away from the optimal, where r is the number of strata. We present S-VOILA, a practical streaming algorithm for SRS that is locally variance-optimal in its allocation of sample sizes to different strata. Our result from experiments on real and synthetic data show that VOILA can have significantly (1.4 to 50.0 times) smaller variance than Neyman allocation. The streaming algorithm S-VOILA results in a variance that is typically close to VOILA, which was given the entire input beforehand.