Computational method for statistical measures of reliability, confidence, and assurance are available for infinite population size. If the population size is finite and small compared to the number of samples tested, these computational methods need to be improved for a better representation of reality. This article discusses how to compute reliability, confidence, and assurance statistics for finite number of samples. Graphs and tables are provided as examples and can be used for low number of test sample sizes. Two open-source python libraries are provided for computing reliability, confidence, and assurance with both infinite and finite number of samples.

翻译：针对无限总体规模的可靠性、置信度与保证度统计量的计算方法已有成熟方案。当总体规模有限且远小于测试样本量时，需改进计算方法以更准确反映实际情况。本文探讨了有限样本下可靠性、置信度与保证度统计量的计算方式，并提供了低测试样本量场景下的示例图表与数据表。同时给出了两个开源Python库，支持无限样本与有限样本场景下的可靠性、置信度与保证度计算。