The distribution of order statistics under sampling without replacement

TL;DR

This paper derives the distribution of order statistics from sampling without replacement, explores its properties, and applies it to population size estimation, providing new theoretical insights and practical algorithms.

Contribution

It introduces a shifted beta-binomial distribution for order statistics under SRSWOR and generalizes it to arbitrary populations, including applications to the German tank problem.

Findings

Distribution relates to beta-binomial distribution

Asymptotic properties derived

Algorithm for sampling without full population generation

Abstract

This paper examines the distribution of order statistics taken from simple-random-sampling without replacement (SRSWOR) from a finite population with values 1,...,N. This distribution is a shifted version of the beta-binomial distribution, parameterised in a particular way. We derive the distribution and show how it relates to the distribution of order statistics under IID sampling from a uniform distribution over the unit interval. We examine properties of the distribution, including moments and asymptotic results. We also generalise the distribution to sampling without replacement of order statistics from an arbitrary finite population. We examine the properties of the order statistics for inference about an unknown population size (called the German tank problem) and we derive relevant estimation results based on observation of an arbitrary set of order statistics. We also introduce an algorithm that simulates sampling without replacement of order statistics from an arbitrary finite population without having to generate the entire sample.