# Concepts

These explanations dive into the what, why and theory behind each of DataEval's features.

- [Balance Bias Metrics](Balance.md)
- [Bayes Error Rate Estimation](BER.md)
- [Bias Detection](Bias.md)
- [Cluster Assignment](Clusterer.md)
- [Coverage Analysis](Coverage.md)
- [Dataset Cleaning](DataCleaning.md)
- [Dataset Divergence](Divergence.md)
- [Diversity Indices](Diversity.md)
- [Drift Detection](Drift.md)
- [Duplicate Detection](Duplicates.md)
- [Label Parity Assessment](LabelParity.md)
- [Metadata](Metadata.md)
- [Model Training Techniques](ModelTraining.md)
- [Out of Distribution Detection](OOD.md)
- [Outliers Class](Outliers.md)
- [Parity Assessment](Parity.md)
- [Statistical Analysis of Images](Stats.md)
- [Sufficiency of Datasets per Model](Sufficiency.md)
- [Upperbound on Average Precision Estimation](UAP.md)


:::{toctree}
:hidden:
:maxdepth: 1

Balance.md
BER.md
Bias.md
Clusterer.md
Coverage.md
DataCleaning.md
Divergence.md
Diversity.md
Drift.md
Duplicates.md
LabelParity.md
Metadata.md
ModelTraining.md
OOD.md
Outliers.md
Parity.md
Stats.md
Sufficiency.md
UAP.md
:::

For a quick reference of each algorithm's functionality and requirements, see the Algorithm Overview page.

[Algorithm Overview](metric_table.md)

:::{toctree}
:hidden:
:maxdepth: 1

metric_table.md
:::