Outliers are data points that differ significantly from other observations. They can indicate measurement errors, data entry mistakes, or genuinely unusual events. Detecting them is crucial before analysis, as outliers can skew means, correlations, and model training. The IQR and Z-score methods are the two most common detection approaches.
How to Use
Enter your dataset:
- Input: Comma or space-separated numbers
- Method: Choose IQR, Z-score, or modified Z-score
- Results: Outliers highlighted with reasons
Detection Methods
- IQR: Values below Q1−1.5×IQR or above Q3+1.5×IQR
- Z-score: Values with |z| > threshold (default 3)
- Modified Z-score: Uses median absolute deviation, robust against outliers
What to Do with Outliers
- Verify data entry for errors
- Investigate if genuine unusual events
- Consider winsorizing or trimming
- Report analysis both with and without outliers
Step-by-Step Instructions
- 1Enter numbers separated by commas or spaces.
- 2Select a detection method.
- 3Adjust the threshold if needed.
- 4Review highlighted outliers.
- 5Check the five-number summary.