# Market Data Hygiene: Statistical Methods for Detecting Problematic Data

This article has been expanded into a three-part series:

- **[Part 1: Statistical Methods for Detecting Bad Data](/content/blog/market-data-hygiene-part-1/index.html)**: Point anomaly detection (tick tests, NBBO, MAD/IQR, volatility-adjusted thresholds) and systematic error identification (staleness, bid-ask inversion, timestamp drift)

- **[Part 2: Cross-Validation and Contextual Analysis](/content/blog/market-data-hygiene-part-2/index.html)**: Cross-asset validation, time-based patterns, venue-specific considerations, and multi-source triangulation

- **[Part 3: Reference Data and Historical Integrity](/content/blog/market-data-hygiene-part-3/index.html)**: Corporate actions, index membership, point-in-time correctness, and building a validation framework

Start with [Part 1](/content/blog/market-data-hygiene-part-1/index.html).