Sequential Unequal Probability Sampling For Stream Population

TL;DR

This paper introduces a sequential unequal probability sampling method suitable for streaming data, enabling adjustable spreading of samples with minimal window size, enhancing sampling efficiency in real-time data streams.

Contribution

It presents a novel sequential sampling technique for streams that uses a minimal sliding window and allows adjustable sample spreading, improving upon existing methods.

Findings

Efficient sampling from data streams with minimal memory.

Adjustable spreading of samples to suit different needs.

Applicable to real-time data analysis scenarios.

Abstract

A new unequal probability sampling method is proposed. This method is sequential. The decision to select or not each unit is made based on the order in which the units appear. A variant of this method allows selecting a sample from a stream. At each step, the decision to take the units successively according to the order of appearance in the stream is made. This method involves using a sliding window that is as small as possible. The method also allows the sample to be spread and even the level of spreading to be adjusted.