|
|
 |
| |
|
|
|
Advancements in Statistical Sampling: Stratified Double Unified Ranked Set Sampling with Perfect Ranking for Symmetric Distributions |
|
|
|
PP: 1501-1514 |
|
|
|
doi:10.18576/jsap/130507
|
|
|
|
Author(s) |
|
|
|
Noppakun Thongmual,
Chainarong Peanpailoon,
|
|
|
|
Abstract |
|
|
| In this comprehensive analysis, we unveil enhancements to a refined sample selection technique known as Stratified Double Unified Ranked Set Sampling with Perfect Ranking, specifically designed to accurately determine the population mean. This innovative methods capability to estimate the population means is rigorously evaluated against three established sampling strategies: Stratified Simple Random Sampling (SSRS), Stratified Ranked Set Sampling (SRSS), and Stratified Median Ranked Set Sampling, also encompassing comparisons with Stratified Double Unified Ranked Set Sampling (SMRSS). Our comparative analysis is meticulously conducted across three symmetric probability distributions: the standard normal distribution, the Student-t distribution, and the uniform distribution (0,1). Through our investigations, we ascertain that the estimator emerging from Stratified Random Sampling, utilizing Two Full Cycles of Systematic Selection within a perfectly ordered set, remains unbiased. This holds true across various sample set sizes (m) - specifically, m = 2, 4, 6, 10 - and during two distinct levels of selection rounds (r), namely r = 2 and 5. This study not only underscores the precision and reliability of the enhanced sampling method but also provides a comparative framework that highlights its superior efficiency in population mean estimation under diverse distribution scenarios. |
|
|
|
|
|
|
|
