Efficient body fat estimation using multistage pair ranked set sampling

Rank-based sampling methods are applicable in settings where precise measurements are expensive, but small sets of units can be accurately ranked at negligible cost. This article introduces one such a design, called multistage pair ranked set sampling. It mitigates ranking burden associated with a c...

Full description

Saved in:
Bibliographic Details
Published in:Statistical methods in medical research 2019-01, Vol.28 (1), p.223-234
Main Authors: Mahdizadeh, M, Zamanzade, Ehsan
Format: Article
Language:English
Subjects:
Absorptiometry, Photon
Adipose Tissue
Biomarkers
Body fat
Humans
Models, Statistical
Multistage
Obesity - diagnosis
Obesity - epidemiology
Overweight - diagnosis
Overweight - epidemiology
Random sampling
Ratings & rankings
Sampling methods
Sampling Studies
Waist Circumference
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rank-based sampling methods are applicable in settings where precise measurements are expensive, but small sets of units can be accurately ranked at negligible cost. This article introduces one such a design, called multistage pair ranked set sampling. It mitigates ranking burden associated with a competitor scheme, namely multistage ranked set sampling. The mean estimator in multistage pair ranked set sampling is unbiased, and under perfect rankings has variance no larger than its simple random sampling counterpart. Although the suggested mean estimator is outperformed by its multistage ranked set sampling analog in terms of precision under perfect rankings, the situation may be reversed if cost considerations are taken into account. The methodology is illustrated using a medical dataset.
ISSN:0962-2802
1477-0334
DOI:10.1177/0962280217720473