Data Explorer & Outlier Detector
Comprehensive data analysis with automatic outlier detection
Data Input
This data explorer is provided for educational purposes. Results are based on the dataset you provide and use standard statistical methods for analysis and outlier detection.
Understanding Outlier Detection
IQR (Interquartile Range) Method
The most common method. Outliers are values that fall below Q1 - 1.5×IQR or above Q3 + 1.5×IQR. This method is intuitive and works well for most datasets.
Z-Score Method
Based on standard deviations from the mean. Values with |z-score| > 3 (or sometimes 2.5) are considered outliers. Assumes data is normally distributed.
Modified Z-Score (MAD)
Uses Median Absolute Deviation instead of standard deviation, making it more robust to outliers themselves. Values with modified z-score > 3.5 are considered outliers.
Why Remove Outliers?
- Improve accuracy of statistical analysis
- Meet assumptions of statistical tests
- Reduce impact of data entry errors
- Better understand typical patterns in data
Caution: Always investigate outliers before removing them. They might represent important real phenomena rather than errors.