One eminent disadvantage of many existing optimal estimators/class of estimators is that they are typically biased. In this article, we proposed an optimum class of unbiased estimators for estimating the population mean under simple random sampling without replacement (SRSWOR) scheme. Proposed class is a blend of three concepts: 1) information on auxiliary variable, 2) the ranks of auxiliary variable and 3) Hartley-Ross type unbiased estimation procedure. Expressions for the bias and the minimum variance of the new class are derived up to first degree of approximation. To highlight the application of proposed class, five real data sets are used. Numerical findings confirm that the new class behaves efficiently as compared to traditional unbiased estimator and other almost unbiased estimators under study. In addition, Monte Carlo simulation study is conducted through two real populations to assess the performance of proposed class against competitors. On the basis of theoretical and numerical findings, it is concluded that new proposed class can generate optimum unbiased estimators under SRSWOR scheme. Therefore, use of proposed class is recommended for future applications.

许多现有的最佳估计量/估计量类别的一个显着缺点是它们通常是有偏差的。在本文中，我们提出了一种最佳的无偏估计量类别，用于估计简单随机抽样无替换（SRSWOR）方案下的总体均值。提议的类是三个概念的混合：1）有关辅助变量的信息，2）辅助变量的等级，以及3）Hartley-Ross类型的无偏估计程序。新类的偏差和最小方差的表达式可以导出到第一近似程度。为了突出建议的类的应用，使用了五个实际数据集。数值结果证实，与传统的无偏估计量和其他正在研究的几乎无偏估计量相比，新类别的行为有效。此外，蒙特卡洛模拟研究是通过两个真实人群进行的，以评估拟议班级与竞争对手的表现。在理论和数值研究的基础上，得出结论，新提出的类可以在SRSWOR方案下生成最优的无偏估计量。因此，建议在将来的应用程序中使用建议的类。