Interquartile Range (IQR)
IQR = Q₃ - Q₁Spread of middle 50% of data
Robust measure of dispersion, unaffected by outliers
Calculate interquartile range (IQR), quartiles, and identify data spread between Q1 and Q3.
https://www.solvezi.com/statistics/interquartile-range-calculator
Understand data spread and identify outliers
| # | Value | Action |
|---|---|---|
| 1 | ||
| 2 | ||
| 3 | ||
| 4 | ||
| 5 | ||
| 6 | ||
| 7 | ||
| 8 | ||
| 9 | ||
| 10 |
10 values (minimum 4 recommended for IQR)
Q₁ (25th)
0.0000
Q₂ (Median)
0.0000
Q₃ (75th)
0.0000
Q₃ - Q₁ = 0.0000 - 0.0000
Lower Fence
0.0000
Q₁ - 1.5×IQR
Upper Fence
0.0000
Q₃ + 1.5×IQR
Lower Whisker
0.0000
Min within fences
Upper Whisker
0.0000
Max within fences
Outliers
None detected
Interpretation
Data dispersion analysis
No variation in data
Min
0.0000
Max
0.0000
Range
0.0000
n
10
Middle 50%
[0.00, 0.00]
What is Interquartile Range (IQR)?
The IQR measures statistical dispersion, representing the middle 50% of data.
• Box Plot: IQR forms the "box" with whiskers extending to min/max within fences
• Outlier Detection: Values beyond Q₁ − 1.5×IQR or Q₃ + 1.5×IQR are outliers
• Robust Measure: Unlike range, IQR is not affected by outliers
IQR Calculator • Understand data spread and identify outliers
Master the Interquartile Range (IQR) — learn to calculate quartiles, identify outliers, understand data spread, and apply robust statistical measures for skewed distributions in quality control, finance, healthcare, and research.
The Interquartile Range (IQR) is the difference between the third quartile (Q₃, 75th percentile) and the first quartile (Q₁, 25th percentile). It measures the spread of the middle 50% of your data.
"How spread out are the middle 50% of my data values — and what values are considered unusual outliers?"
25% of data falls below this value
Middle value, 50% below, 50% above
75% of data falls below this value
IQR = Q₃ - Q₁Spread of middle 50% of data
Robust measure of dispersion, unaffected by outliers
Lower Fence = Q₁ - 1.5 × IQRThreshold for lower outliers
Values below are potential outliers
Upper Fence = Q₃ + 1.5 × IQRThreshold for upper outliers
Values above are potential outliers
Smallest value ≥ Lower FenceBottom of data range (excluding outliers)
Shown as bottom line in box plot
Largest value ≤ Upper FenceTop of data range (excluding outliers)
Shown as top line in box plot
Values < L.Fence or > U.FenceExtreme values beyond fences
Plotted as individual points in box plot
Arrange all values in ascending order
Locate middle value. For even n, average two middle values
Median of lower half of data (values below Q₂)
Median of upper half of data (values above Q₂)
IQR = Q₃ - Q₁
Lower = Q₁ - 1.5×IQR, Upper = Q₃ + 1.5×IQR
Min/Max values within fences
Values beyond fences are potential outliers
Median of lower/upper halves including median if odd nBest for: General purpose, box plots
Standard method for exploratory data analysis
Median of lower/upper halves excluding medianBest for: Statistical software compatibility
Used by many textbook authors
Position = (n+1)/4, (n+1)/2, 3(n+1)/4Best for: Consistent with percentile definitions
Interpolates between values
Best for: General outlier detection
Standard for box plots, identifies potential outliers
Best for: Extreme outlier identification
More conservative, marks only far outliers
Best for: Normal distributions
Assumes normality, less robust
Best for: Robust detection
More robust than IQR for some distributions
Pro Tip: The 1.5×IQR rule identifies potential outliers. Always investigate outliers before removing them — they may reveal important insights or data quality issues.
Identify production variations and quality issues
Measure investment risk and return variability
Understand patient outcome ranges
Evaluate assessment fairness and outcome ranges
Monitor environmental patterns and extremes
Understand data spread before modeling
Small relative to range
Data concentrated near median
Large relative to range
Data spread out widely
Symmetric around median
Approximately symmetric distribution
Skewed box in box plot
Skewed distribution
Best for:
Quick spread estimate, symmetric data
Limitation:
Highly sensitive to outliers
Best for:
Skewed distributions, outlier-resistant summary
Limitation:
Ignores tails, less powerful for normal data
Best for:
Normal distributions, parametric tests
Limitation:
Sensitive to outliers, assumes normality
Best for:
Highly robust dispersion measure
Limitation:
Less common, harder to interpret
Using different quartile calculation methods without noting
Always specify which method you used (Tukey is standard)
Our calculator uses Tukey's method (including median in halves for odd n)
Calling all points beyond fences 'bad data'
Outliers may be valid extreme values, not errors
Investigate outliers — they might be the most interesting findings!
Using IQR for bimodal distributions
IQR may not represent typical spread for multimodal data
Check histogram shape before relying solely on IQR
Confusing IQR with range
Range = Max - Min (affected by outliers), IQR = Q₃ - Q₁ (robust)
Use IQR for skewed data, range for symmetric data without outliers
IQR is robust to outliers, making it better for skewed distributions. Standard deviation gives more weight to extreme values. For normally distributed data, both are useful; for skewed data (like income, house prices), IQR better represents typical spread. IQR is also more intuitive for non-statisticians.
IQR becomes more stable with larger samples (n ≥ 30). For very small samples (n < 10), quartiles may not be well-defined and IQR can be unreliable. Small samples may produce unstable outlier detection. Our calculator warns when sample size is insufficient for reliable analysis.
No, IQR requires ordered numeric data. For ordinal data (ranked categories), percentiles can still be meaningful, but interpretation differs. For nominal categories, use mode and frequency distributions instead. IQR specifically measures numeric spread of continuous or discrete numeric data.
In standard Tukey box plots, whiskers extend to the smallest and largest values within 1.5×IQR of the quartiles. Points beyond become outliers. Some variations use percentiles (5th/95th) for whiskers, but the 1.5×IQR rule is most common and balances outlier detection with data representation.
First, investigate if outliers are data entry errors. If valid, consider: 1) Report both with and without outliers, 2) Use robust statistics (median, IQR), 3) Transform data (log transformation), 4) Use non-parametric tests. Never arbitrarily remove outliers without justification.
Quartile deviation (semi-interquartile range) is half the IQR: QD = (Q₃ - Q₁)/2. It measures average distance from quartiles to median, but IQR is more commonly reported. Some fields use quartile deviation as a measure of dispersion, but IQR is standard in most statistical software.
MAD = median(|xᵢ - median|) is another robust dispersion measure. MAD is even more resistant to outliers than IQR but less commonly used. For normally distributed data, MAD ≈ 0.6745 × standard deviation. IQR is preferred for box plots and outlier detection with the 1.5×IQR rule.
Yes, IQR = 0 when Q₁ = Q₃, meaning at least 50% of data points have the same value. This suggests many repeated values or very low variability. In such cases, outlier detection using the 1.5×IQR rule may not be meaningful — consider alternative methods or investigate data quality.
1915-2000
Popularized IQR and 1.5×IQR rule for box plots (1977)
Also coined 'bit' and 'software', developed FFT algorithm
1822-1911
Early work on percentiles and quantiles
Founded psychometrics and eugenics
1857-1936
Developed quartile concepts
Father of mathematical statistics
Did You Know? John Tukey invented the box plot in 1977 as part of his Exploratory Data Analysis framework. The 1.5×IQR rule for outliers was chosen empirically — it works well for normal distributions (marking about 0.7% of data as outliers) while being robust for other distributions. Tukey also coined the terms "bit" and "software"!
Box Plot Components:
What Box Plot Shows:
Interquartile Range calculator and complete guide. Calculate Q1, Q2, Q3, IQR, fences, whiskers, and outliers using Tukey's method. Learn quartile calculation, outlier detection with the 1.5×IQR rule, and applications in quality control, finance, healthcare, and data science.