• Verify the validity of outliers by cross-checking with original records.
• Correct errors, if any, or document them for exclusion in analysis if they are implausible.
• Use statistical methods to detect and manage legitimate outliers without excluding important variability. For example, a record showing 32 decayed teeth could result from a misentry for "3-2," requiring correction.

Citation: Osborne, J. W., & Overbay, A. (2004). The power of outliers and why researchers should always check for them. Practical Assessment, Research, and Evaluation, 9(1), 6.