A Bayesian Approach to Biological Variation Analysis.
Journal
Clinical chemistry
ISSN: 1530-8561
Titre abrégé: Clin Chem
Pays: England
ID NLM: 9421549
Informations de publication
Date de publication:
08 2019
08 2019
Historique:
received:
26
11
2018
accepted:
13
05
2019
pubmed:
3
7
2019
medline:
17
4
2020
entrez:
3
7
2019
Statut:
ppublish
Résumé
Biological variation (BV) data have many applications for diagnosing and monitoring disease. The standard statistical approaches for estimating BV are sensitive to "noisy data" and assume homogeneity of within-participant CV. Prior knowledge about BV is mostly ignored. The aims of this study were to develop Bayesian models to calculate BV that ( We explored Bayesian models with different degrees of robustness using adaptive Student Using the most robust Bayesian approach on a raw data set gave results comparable to a standard approach with outlier assessments and removal. The posterior distribution of the fitted model gives access to credible intervals for all parameters that can be used to assess reliability. Reliable and relevant priors proved valuable for prediction. The recommended Bayesian approach gives a clear picture of the degree of heterogeneity, and the ability to crudely estimate personal within-participant CVs can be used to explore relevant subgroups. Because BV experiments are expensive and time-consuming, prior knowledge and estimates should be considered of high value and applied accordingly. By including reliable prior knowledge, precise estimates are possible even with small data sets.
Sections du résumé
BACKGROUND
Biological variation (BV) data have many applications for diagnosing and monitoring disease. The standard statistical approaches for estimating BV are sensitive to "noisy data" and assume homogeneity of within-participant CV. Prior knowledge about BV is mostly ignored. The aims of this study were to develop Bayesian models to calculate BV that (
METHOD
We explored Bayesian models with different degrees of robustness using adaptive Student
RESULTS
Using the most robust Bayesian approach on a raw data set gave results comparable to a standard approach with outlier assessments and removal. The posterior distribution of the fitted model gives access to credible intervals for all parameters that can be used to assess reliability. Reliable and relevant priors proved valuable for prediction.
CONCLUSIONS
The recommended Bayesian approach gives a clear picture of the degree of heterogeneity, and the ability to crudely estimate personal within-participant CVs can be used to explore relevant subgroups. Because BV experiments are expensive and time-consuming, prior knowledge and estimates should be considered of high value and applied accordingly. By including reliable prior knowledge, precise estimates are possible even with small data sets.
Identifiants
pubmed: 31263036
pii: clinchem.2018.300145
doi: 10.1373/clinchem.2018.300145
doi:
Substances chimiques
Chlorides
0
Triglycerides
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
995-1005Informations de copyright
© 2019 American Association for Clinical Chemistry.