EUVIMEDEUVIMED entdecken
Crossref

Estimation of Population Mean Using Calibrated Weights in Stratified Random Sampling: A Theoretical and Simulation Study

U. Shanmukha Rao, Menaka Bammidi

International Journal of Drug Delivery Technology · 01.06.2026 · 16 (41s)

DOI: 10.25258/ijddt.16.41s.65 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 01.06.2026. Verfasst von U. Shanmukha Rao und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate estimation of the population mean is a foundational problem in survey sampling, particularly in large-scale stratified designs where auxiliary information is available. Classical estimators such as the Horvitz–Thompson (HT) estimator discard this information, leading to suboptimal precision. This paper proposes a calibrated weight estimator for the population mean within a stratified random sampling framework, utilizing known population-level auxiliary totals to construct optimal calibration weights via a generalized regression (GREG) formulation. We derive the calibrated estimator, establish its asymptotic properties including approximate unbiasedness and variance expression, and introduce a relative efficiency measure to benchmark performance gains. An extensive Monte Carlo simulation study with 10,000 replications across varying correlation levels (ρ = 0.3, 0.5, 0.7, 0.9) and sample sizes (n = 50, 100, 200) demonstrates that the calibrated estimator consistently achieves lower mean squared error (MSE) than both the HT and ratio estimators, with efficiency gains reaching up to 42% under high-correlation scenarios. The theoretical results are supported by empirical evidence, and conditions under which calibration provides the greatest benefit are systematically characterized. Applications to socio-economic survey design are discussed, and directions for extending the framework to multivariate auxiliary information and non-linear calibration functions are outlined.

Zitieren

APA

Rao, U. S., & Bammidi, M. (2026). Estimation of Population Mean Using Calibrated Weights in Stratified Random Sampling: A Theoretical and Simulation Study. International Journal of Drug Delivery Technology, 16(41s). https://doi.org/10.25258/ijddt.16.41s.65

Vancouver

Rao US, Bammidi M. Estimation of Population Mean Using Calibrated Weights in Stratified Random Sampling: A Theoretical and Simulation Study. International Journal of Drug Delivery Technology. 2026;16(41s). doi:10.25258/ijddt.16.41s.65

BibTeX
@article{Rao2026,
  author = {Rao, U. Shanmukha and Bammidi, Menaka},
  title = {Estimation of Population Mean Using Calibrated Weights in Stratified Random Sampling: A Theoretical and Simulation Study},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {41s},
  doi = {10.25258/ijddt.16.41s.65}
}
Kostenlos starten →