This R package determines optimal stratification of univariate populations under stratified sampling designs using a parametric‐based method. It determines the optimum strata boundaries (OSB), optimum sample sizes (OSS) and multiple other quantities for the study variable, y, using the best‐fit probability density function of a study variable available from survey data. The method requires the parameters and other characteristics of the distribution of the study variable to be known, either from available data or from a hypothetical distribution if the data are not available. In the implementation, the problem of determining the OSB is formulated as a mathematical programming problem and solved by using a dynamic programming technique. If the data of the population (i.e. the study variable) are available to the surveyor, the method estimates its best‐fit distribution and determines the OSB and OSS under Neyman allocation, directly. When the dataset is not available, stratification is made based on the assumption that the values of the study variable, y, are available as hypothetical realisations of proxy values of y from past/recent surveys. Thus, it requires certain distributional assumptions about the study variable. At present, the package handles stratification for the populations where the study variable follows a continuous distribution: namely, Pareto, Triangular, Right‐triangular, Weibull, Gamma, Exponential, Uniform, Normal, Lognormal and Cauchy distributions. In this paper, applications of major functionalities in the package are illustrated with a number of real/simulated as well as some hypothetical populations.

中文翻译：

---

stratifyR：R包，用于单变量总体的最佳分层和样本分配

此R包使用基于参数的方法确定分层抽样设计下的单变量总体最优分层。它确定研究变量y的最佳地层边界（OSB），最佳样本量（OSS）和其他多个数量，使用调查数据中可用的研究变量的最佳拟合概率密度函数。该方法要求研究变量分布的参数和其他特征是已知的，可以从可用数据中获得，也可以从假设分布中获得（如果数据不可用时）。在实现中，确定OSB的问题被表述为数学编程问题，并通过使用动态编程技术来解决。如果测量员可以获得总体数据（即研究变量），则该方法将估计其最佳拟合分布，并直接在Neyman分配下确定OSB和OSS。当数据集不可用时，根据研究变量y的值进行分层可以用作过去/最近调查的y代理值的假设实现。因此，它需要有关研究变量的某些分布假设。目前，该软件包处理研究变量遵循连续分布的人群的分层：即帕累托，三角，右三角形，威布尔，伽马，指数，均匀，正态，对数正态和柯西分布。在本文中，通过大量的实际/模拟以及一些假设的种群来说明该软件包中主要功能的应用。