Unequal probability sampling is commonly used for sample selection. In the context of spatial sampling, the variables of interest often present a positive spatial correlation, so that it is intuitively relevant to select spatially balanced samples. In this article, we study the properties of pivotal sampling and propose an application to tesselation for spatial sampling. We also propose a simple conservative variance estimator. We show that the proposed sampling design is spatially well balanced, with good statistical properties and is computationally very efficient.

中文翻译：

---

关键采样下的推理：属性，方差估计及其在镶嵌中的空间采样应用

不等概率抽样通常用于样本选择。在空间采样的情况下，感兴趣的变量通常呈现正的空间相关性，因此选择空间平衡的样本在直观上是相关的。在本文中，我们研究了枢轴采样的特性，并提出了在镶嵌细分中进行空间采样的应用。我们还提出了一个简单的保守方差估计量。我们表明，提出的抽样设计在空间上平衡良好，具有良好的统计特性，并且计算效率很高。