Related Experiment Video
Updated: Jun 26, 2026
07:35
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
Statistical evaluation of quality performance on genomic composite biomarker classifiers.
1Division of Biometry, Graduate Institute of Agronomy, National Taiwan University, Taipei, and Division of Biostatistics and Bioinformatics, National Health Research Institutes, Zhunan, Taiwan. jpliu@ntu.edu.tw
Journal of the Formosan Medical Association = Taiwan Yi Zhi
|January 9, 2009
Summary
New statistical methods evaluate genomic composite biomarker classifiers (GCBCs) for gene expression, agreement, and reproducibility. These validated techniques ensure reliable performance of GCBCs in research and clinical applications.
Area of Science:
- Genomics
- Biostatistics
- Biomarker Discovery
Background:
- Genomic composite biomarker classifiers (GCBCs) emerged post-Human Genome Project.
- The performance quality of GCBCs is known to vary significantly.
Purpose of the Study:
- To develop and validate statistical methods for assessing GCBC quality.
- Focus on evaluating differentially expressed genes, technical agreement, and inter-laboratory reproducibility.
Main Methods:
- An interval hypothesis approach for detecting differentially expressed genes, balancing biological and statistical significance.
- Concordance correlation coefficient (CCC) for assessing technical replicate agreement.
- Intraclass correlation coefficient (ICC) for evaluating inter-laboratory reproducibility.
Main Results:
- A two one-sided test procedure effectively tested the interval hypothesis for gene expression.
- Generalized pivotal quantities provided robust hypothesis testing for CCC and ICC.
- Simulation studies confirmed all three methods adequately controlled type I error rates.
Conclusions:
- Three robust statistical methods were developed for GCBC quality assessment.
- These methods address key performance metrics: differential expression, agreement, and reproducibility.
- The validated methods enhance the reliability and trustworthiness of GCBCs.
