A general variance model in methods comparison

Valid statistical tests of paired data require correct models of how measurement variance depends on analyte concentration. One often‐used assumption is that the variance is constant across the range; another is that the coefficient of variation is constant. But in many data sets, neither of these h...

Full description

Saved in:
Bibliographic Details
Published in:Journal of chemometrics 2013-11, Vol.27 (11), p.414-419
Main Author: Hawkins, Douglas M.
Format: Article
Language:English
Subjects:
Chemistry
Coefficient of variation
Comparative analysis
Deming regression
diagnostic plotting
matched-pairs data
Measurement
Regression analysis
Simulation
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:Valid statistical tests of paired data require correct models of how measurement variance depends on analyte concentration. One often‐used assumption is that the variance is constant across the range; another is that the coefficient of variation is constant. But in many data sets, neither of these holds. A variance model containing both a constant variance and a constant coefficient of variation term is recommended as an often‐useful additional analysis tool for methods comparison. The more general variance model is fitted to a simulated data set, and one from a clinical chemistry methods comparison. It is used to provide more reliable average versus difference plots, to fit weighted Deming regressions, and to provide valid paired data analyses. The calculations are implemented in r software. Copyright © 2013 John Wiley & Sons, Ltd. Data pairs in methods comparisons frequently follow neither constant variance nor the constant coefficient of variation assumptions, invalidating conventional statistical analyses. A more general variance model provides additional statistical tools for analysis of such data.
ISSN:0886-9383
1099-128X
DOI:10.1002/cem.2550