Identify outliers in your dataset using multiple detection methods: IQR (Tukey's fences), Z-Score, and Modified Z-Score. Compare methods, visualize results with box plots, and analyze each data point.
You might also find these calculators useful
Identify outliers in any dataset using multiple statistical methods. Compare IQR (Tukey's fences), Z-Score, and Modified Z-Score detection. View results with box plot visualization and detailed data point analysis.
Outliers are data points that differ significantly from other observations. They may indicate measurement errors, data entry mistakes, or genuinely unusual values. Detecting outliers is crucial for data quality, statistical analysis, and machine learning. Common detection methods include the IQR method (using Tukey's fences), Z-Score method (measuring standard deviations from mean), and Modified Z-Score (using median and MAD for robustness).
IQR Method Formula
Outlier if x < Q₁ - 1.5×IQR or x > Q₃ + 1.5×IQRIdentify and handle erroneous data points before analysis or modeling.
Detect manufacturing defects or process anomalies using statistical control limits.
Identify unusual transactions or patterns that may indicate fraudulent activity.
Find unusual observations that may lead to new discoveries or indicate experimental errors.
The IQR (Interquartile Range) method, also known as Tukey's fences, identifies outliers as values below Q1 - 1.5×IQR or above Q3 + 1.5×IQR (mild outliers). Extreme outliers fall outside Q1 - 3×IQR and Q3 + 3×IQR. This method is robust and works well with skewed data.