Extreme Population Selection under Multistage Sampling design With Applications
Abstract
We study the problem of selecting the extreme (best or worst) population from among K(≥ 2) populations, under the assumption that the extreme population is sufficiently separated from the nearest population. The selection is based on an appropriate measure, which may vary across different application domains. Since the actual value of the measure is unknown, we obtain its estimator using the generalized method of moments under a multistage sampling design. Using this estimator, we propose two sequential procedures, namely online algorithm and multi armed bandit based algorithm. Under suitable regularity conditions and without imposing parametric assumptions on the underlying distributions, both algorithms correctly identify the extreme population with a desired level of confidence. We illustrate the proposed algorithms through applications in econometrics and genetics. In the econometric application, the extreme population is selected using the Gini index as a measure of inequality and the performance of the proposed procedures is assessed through extensive Monte Carlo simulation studies conducted under various distributional settings. In the genetics application, the worst population is identified using a measure derived from the tumor mutation burden (TMB) score and the practical applicability of the proposed algorithms is demonstrated using the Memorial Sloan Kettering-IMPACT 50000 clinical sequencing cohort. Further, we use the proposed framework to identify an anomalous population, provided such a population exists.
Related
- Transformation of Adaptive Multistage Sampling for Solving Finite-Horizon Markov Decision Processes with Unknown Model
- Finite-population inference for cross-fitted estimators of treatment contrasts in stratified multistage surveys
- When n is not enough: Assessing the interplay of spatial sampling error and sample selection in abundance estimation
- Information-Geometric Selection for Validation-Guided Ensembles of Extreme Learning Machines: The LEA-EELM Framework
- Designing multi‐site studies for external validity: Site selection via synthetic purposive sampling
BibTeX
@misc{shivam2026extreme,
title = {{Extreme Population Selection under Multistage Sampling design With Applications}},
author = {Shivam and Bhargab Chattopadhyay and Nil Kamal Hazra},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28127},
eprint = {2609.28127},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28127},
}
RIS
TY - UNPB
TI - Extreme Population Selection under Multistage Sampling design With Applications
AU - Shivam
AU - Bhargab Chattopadhyay
AU - Nil Kamal Hazra
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.28127
UR - https://arxiv.org/abs/2609.28127
AB - We study the problem of selecting the extreme (best or worst) population from among K(≥ 2) populations, under the assumption that the extreme population is sufficiently separated from the nearest population. The selection is based on an appropriate measure, which may vary across different application domains. Since the actual value of the measure is unknown, we obtain its estimator using the generalized method of moments under a multistage sampling design. Using this estimator, we propose two sequential procedures, namely online algorithm and multi armed bandit based algorithm. Under suitable regularity conditions and without imposing parametric assumptions on the underlying distributions, both algorithms correctly identify the extreme population with a desired level of confidence. We illustrate the proposed algorithms through applications in econometrics and genetics. In the econometric application, the extreme population is selected using the Gini index as a measure of inequality and the performance of the proposed procedures is assessed through extensive Monte Carlo simulation studies conducted under various distributional settings. In the genetics application, the worst population is identified using a measure derived from the tumor mutation burden (TMB) score and the practical applicability of the proposed algorithms is demonstrated using the Memorial Sloan Kettering-IMPACT 50000 clinical sequencing cohort. Further, we use the proposed framework to identify an anomalous population, provided such a population exists.
ER -