Abstract Revisiting Stein (1945, 1949) as well as Mukhopadhyay and Duggan (1997), we have proposed new two-stage procedures under both minimum risk point estimation and fixed-width confidence interval configurations for a normal mean μ when a lower bound of variance is known to us. New unbiased estimators based on sample standard deviation, Gini’s mean difference (GMD), and mean absolute deviance (MAD) are constructed to define the final sample sizes. The new procedures enjoy both asymptotic first-order and second-order properties, followed by simulated performances. Real data illustrations of the marigold data are also included.

中文翻译：

---

具有已知方差下限的正态均值的两阶段估计，最终样本量通过基尼平均差和平均绝对偏差定义

摘要 回顾 Stein (1945, 1949) 以及 Mukhopadhyay 和 Duggan (1997)，我们提出了新的两阶段程序，在最小风险点估计和固定宽度置信区间配置下，当方差下限为正态均值 μ 时我们知道。构建了基于样本标准偏差、基尼平均差 (GMD) 和平均绝对偏差 (MAD) 的新无偏估计量，以定义最终样本量。新程序具有渐近一阶和二阶特性，然后是模拟性能。还包括万寿菊数据的真实数据插图。