Fact-checked by Grok 2 weeks ago

Interquartile range

The interquartile range (IQR), also known as the midspread or middle 50%, is a robust measure of that quantifies the spread of the middle 50% of a by calculating the difference between the third (Q3, the 75th ) and the first (Q1, the 25th ). Unlike the full range, which can be heavily influenced by extreme outliers, the IQR focuses solely on the central portion of the data, providing a more stable indicator of variability that is less sensitive to anomalies. To compute the IQR, a is first ordered from lowest to highest value, after which the quartiles are determined: divides the lower half at the 25th , and Q3 divides the upper half at the 75th , with the (Q2) marking the 50th in between. The is simply IQR = Q3 - , often derived using methods like the true index location for precise positioning in continuous data. For example, in a with = 80 and Q3 = 90, the IQR equals 10, indicating moderate spread in the central values. This measure is particularly valuable in for comparing distributions across groups, as a larger IQR signifies greater variability in the core data. The IQR plays a central role in exploratory data analysis, notably within box plots (or box-and-whisker plots), where it forms the length of the central "box" to visualize the five-number summary: minimum, Q1, median, Q3, and maximum. It is also widely used for outlier detection via the 1.5-IQR rule, classifying values below Q1 - 1.5 × IQR or above Q3 + 1.5 × IQR as potential outliers, which helps in identifying data anomalies without assuming normality. Due to its non-parametric nature, the IQR is applicable to skewed or non-normal distributions and is preferred in fields like finance, environmental science, and quality control for summarizing variability robustly.

Fundamentals

Definition

The interquartile range (IQR), also known as the midspread or middle 50%, is a measure of calculated as the difference between the third quartile (Q3) and the first (Q1) of a . Q1 corresponds to the 25th , marking the value below which 25% of the observations fall when the are ordered from lowest to highest, while Q3 is the 75th , below which 75% of the observations lie. Thus, the IQR quantifies the spread of the central 50% of the , providing insight into the variability within the core distribution without considering extreme values. The formula for the interquartile range is: \text{IQR} = Q_3 - Q_1 This simple yields a non-negative value that directly reflects the width of the interquartile interval, offering a straightforward indicator of spread in ordered distributions. Unlike the full range or standard deviation, the IQR is particularly robust to outliers and extreme values, as it focuses solely on the middle half of the and ignores the lowest 25% and highest 25% of observations. This resistance to and anomalies makes it a preferred measure of in datasets with potential irregularities, such as those in empirical sciences. The concept of the interquartile range was introduced by in his 1882 "Report of the Anthropometric Committee," where he employed it as part of quartile-based statistical analysis for measuring variation in human measurements. 's work in the late laid foundational groundwork for modern , emphasizing quartile methods over more sensitive alternatives.

Quartiles

Quartiles are specific quantiles that divide an ordered into four equal parts, each containing 25% of the observations. The first , denoted as , marks the value below which 25% of the data lies; the second , Q2, is the , with 50% of the data below it; and the third , Q3, indicates the value below which 75% of the data falls. These divisions provide a framework for understanding the distribution's central and spread characteristics without assuming . In notation, Q1 separates the lowest 25% of the data from the remaining 75%, while Q3 delineates the upper 25% from the lower 75%, with the span between Q1 and Q3 encompassing the middle 50% of the observations. The interquartile range, defined as the distance from Q1 to Q3, captures this central portion. The positioning of quartiles in an ordered depends on the sample size. For odd sample sizes, quartiles often align with specific data points or averages of adjacent points in the sorted list; for even sample sizes, —such as averaging the two middle values for the or linearly interpolating between points for Q1 and Q3—ensures precise placement, particularly in continuous data distributions. Visually, quartiles are represented on a number line by marking Q1, Q2, and Q3 to illustrate the data's segmentation into quarters, highlighting the relative positions and gaps between them. In a cumulative distribution function, these points correspond to the 0.25, 0.50, and 0.75 probability levels, providing a graphical view of the data's progression.

Calculation

Methods for Quartiles

Determining quartiles from a requires the data in ascending order and identifying specific positions within the ordered list. The general step-by-step process involves calculating the position for the first quartile (Q1) at (n+1)/4 and the third quartile (Q3) at $3(n+1)/4, where n is the sample size; if these positions are not integers, is typically applied between adjacent data points. For discrete data or ties, methods may select the nearest observation or average values at the position to handle multiplicity. One common approach is Tukey's hinges method, an inclusive technique that divides the dataset into halves while including the in both the lower and upper portions for odd-sized samples. To compute, first find the at position (n+1)/2; then determine the hinge depths as (n+1)/4 from each end, taking the median of the respective halves (including the overall if n is odd). For example, with an odd n=9, the lower hinge (Q1) is the median of the first five values, and the upper hinge (Q3) is the median of the last five. This method, introduced by in , avoids interpolation and yields robust values for box plots. In contrast, the Moore and McCabe method employs an exclusive approach, splitting the data into halves while excluding the from both for odd n to ensure equal-sized groups. After , compute the (Q2); then take Q1 as the median of the lower half (first \lfloor n/2 \rfloor values) and Q3 as the median of the upper half (last \lfloor n/2 \rfloor values). For even n, the halves are naturally equal without exclusion. This technique, detailed in introductory statistics texts, often results in Q1 and Q3 positioned farther from the than in inclusive methods, particularly for small odd samples. A more systematic framework is provided by Hyndman and Fan, who outlined nine algorithms for sample , including quartiles, emphasizing properties like and reduction. These methods compute the position as g(p, n) = (n-1)p + 1 or variants, with r between floor and ceiling indices, where p=0.25 for Q1 and p=0.75 for Q3. Widely adopted are type 7 (default in , using g(p,n) = p(n-1) + 1) and type 8 (recommended by the authors for median-unbiased estimates, adjusting with n + 1/3). Type 6, another common variant, uses p(n+1). These continuous methods handle ties by linear weighting and are preferred in for large datasets. Software implementations vary, leading to differences in quartile values across tools. In R, the quantile() function defaults to type 7 but allows selection up to type 9, aligning with Hyndman and Fan's classifications. Excel's QUARTILE.INC uses linear interpolation over the inclusive range [0,1], computing positions as $1 + (n-1)p, while QUARTILE.EXC excludes endpoints for [1/(n+1), n/(n+1)]. Python's NumPy percentile function, used for quartiles via 25 and 75, defaults to linear interpolation (method='linear'), weighting between adjacent points at non-integer positions, with options for other schemes like 'nearest' for discrete handling. These variations underscore the need to specify the method when comparing results.

Computing the IQR

The interquartile range (IQR) is calculated by subtracting the first quartile (Q1) from the third quartile (Q3) of a , providing a measure of the spread of the central 50% of the . This simple subtraction formula, IQR = Q3 - Q1, assumes that Q1 and Q3 have already been determined from the sorted using a consistent method. To apply it step-by-step, first sort the in ascending order, identify the positions for Q1 (25th ) and Q3 (75th ), compute those values, and then perform the subtraction; the result is robust for most continuous distributions but requires care with discrete or tied . For a worked example with a small hypothetical of n=8 sorted values—3, 5, 7, 8, 12, 13, 14, 21— is the of the lower half (values 3, 5, 7, 8), which is the of the 2nd and 3rd values: (5 + 7)/2 = 6. Similarly, Q3 is the of the upper half (12, 13, 14, 21), the of the 2nd and 3rd values: (13 + 14)/2 = 13.5. Thus, IQR = 13.5 - 6 = 7.5, capturing the variability excluding the lowest and highest values. The choice of quartile computation can influence the IQR value, especially in small or datasets, as there are at least nine common definitions for sample quantiles that differ in and approaches. For instance, methods emphasizing median-unbiasedness (e.g., types 7–9 in Hyndman and Fan's ) tend to yield more consistent IQR estimates for limited data compared to inverse empirical methods. In cases of small sample sizes (n < 4), the IQR depends on the method and is often not reliable, as the data lack sufficient points to separate distinct quartiles meaningfully; such computations are generally avoided due to lack of reliability. For , Q1 and Q3 coincide, resulting in IQR = 0. For n=2, the IQR depends on the : discrete methods (types 1–3) give the full , while interpolation methods (types 6–9) give half the . For n=3, the IQR also varies by : discrete approaches (types 1–3) yield the full , whereas interpolation methods (types 6–9) typically produce half the . For instance, in R's default (type 7), n=2 and n=3 yield IQR = 0.5 × . The IQR demonstrates and resistance to extreme values, as it ignores the lowest 25% and highest 25% of the data, making it less affected by outliers than the full . In the earlier example, the full range is 21 - 3 = 18, heavily influenced by the extremes, whereas the IQR of 7.5 remains unchanged even if the dataset includes additional outliers like replacing 21 with 100.

Applications

Measure of Variability

The interquartile range (IQR) serves as a non-parametric measure of , specifically quantifying the spread of the central 50% of a by calculating the difference between the third (Q3) and the first (Q1). This approach focuses on the middle half of the data, making it particularly suitable for datasets that exhibit or deviations from , where traditional measures may be distorted by extreme values. As a robust , the IQR provides a reliable indicator of variability without assuming an underlying , which enhances its utility in across various fields such as , , and social sciences. In comparison to other measures of variability, the IQR offers distinct advantages over the , which simply subtracts the minimum from the maximum value and is highly sensitive to outliers, potentially exaggerating the perceived spread in contaminated datasets. Unlike the standard deviation, which relies on the and assumes approximate for meaningful interpretation, the IQR remains stable even in non-normal distributions and avoids the influence of tail extremes. Another robust alternative, the (MAD), measures spread around the using absolute differences but typically scales differently from the IQR, with the latter often preferred for its quartile-based focus on interpercentile intervals; both outperform the standard deviation in the presence of outliers. A larger IQR signifies greater variability within the middle 50% of the , offering an intuitive of how dispersed the core observations are relative to the , and it is commonly included in summaries alongside measures of like the . This makes it valuable for summarizing datasets in reports or visualizations, where it helps convey the typical of values without being swayed by anomalies. However, the IQR has limitations, as it ignores the full extent of the by excluding the lowest 25% and highest 25%, thereby failing to capture overall or the behavior in the tails of the . Additionally, its non-parametric nature renders it less amenable to further mathematical manipulations compared to variance-based measures.

Outlier Detection

The interquartile range (IQR) serves as a robust tool for identifying in univariate data sets by establishing bounds that highlight values deviating significantly from the central 50% of the data. The standard method, known as Tukey's fences, defines an outlier as any data point falling below the first quartile (Q1) minus 1.5 times the IQR or above the third quartile (Q3) plus 1.5 times the IQR. This approach, introduced by John W. Tukey in his seminal work on , leverages the non-parametric nature of quartiles to resist the influence of extreme values themselves. To apply this method, one first computes the IQR as Q3 minus Q1, then calculates the lower as Q1 - 1.5 × IQR and the upper as Q3 + 1.5 × IQR. points outside these fences are flagged as potential outliers for further . This process is particularly useful in , where it helps prioritize anomalous observations without assuming a specific . Variations of the rule adjust the multiplier to distinguish between mild and extreme outliers or to suit domain-specific tolerances. For instance, a multiplier of 1.5 identifies mild outliers, while 3.0 flags extreme outliers beyond further extended fences (Q1 - 3 × IQR and Q3 + 3 × IQR), allowing analysts to differentiate levels of deviation. These multipliers can be tuned based on the data's context, such as increasing them for skewed distributions or financial data where extremes may represent valid events like market crashes. While effective for data cleaning and anomaly flagging, the IQR-based method is not definitive, as it may incorrectly label valid extremes—such as natural variations in biological or environmental data—as outliers, especially in heavy-tailed or distributions. Thus, flagged points warrant contextual review to avoid discarding meaningful information.

Examples

Tabular Data Set

To demonstrate the calculation of the interquartile range, consider a sample consisting of 11 test scores: 22, 24, 26, 28, 29, 31, 35, 37, 41, 53, 64. These values represent a small, representative set for illustrating the process. The data must first be arranged in ascending order, as follows:
PositionSorted Value
122
224
326
428
529
631
735
837
941
1053
1164
The steps to compute the and IQR are as follows. The overall is the 6th value in the sorted list, which is 31. The lower half comprises the first 5 values (22, 24, 26, 28, 29); its is the 3rd value, 26, so the first Q1 = 26. The upper half comprises the last 5 values (35, 37, 41, 53, 64); its is the 3rd value, 41, so the third Q3 = 41. The interquartile range is then Q3 - Q1 = 41 - 26 = 15. This IQR of 15 indicates the spread of the middle 50% of the data, which spans from 26 to 41 and shows moderate variability within the central portion of the distribution. As an , the 1.5 × IQR rule can flag potential , where values below - 1.5 × IQR or above Q3 + 1.5 × IQR are considered outliers; here, 1.5 × 15 = 22.5, yielding a lower of 26 - 22.5 = 3.5 and an upper of 41 + 22.5 = 63.5, so the value 64 is flagged as a potential outlier.

Box Plot Illustration

The , a graphical method for summarizing data distribution introduced by , visually represents the interquartile range (IQR) as the central box spanning from the first quartile () to the third quartile (Q3), enclosing the middle 50% of the observations. A horizontal or vertical line within this box marks the , providing a quick view of relative to the data's spread. The box's length directly corresponds to the IQR, highlighting variability in the core data without influence from extreme values. Whiskers extend from the box edges to the adjacent values, defined as the farthest points within 1.5 times the IQR below or above Q3; these limits form "fences" that help identify potential outliers as individual points beyond the . For instance, consider a simple of exam scores: , 60, 65, 70, 72, 75, 78, 80, 85, 90, 95, 100. Here, is 67.5, the is 76.5, and Q3 is 87.5, yielding an IQR of 20. The box would span 67.5 to 87.5, with the median line at 76.5; reach to (minimum) and 100 (maximum), showing no outliers since all values fall within the fences (37.5 to 117.5). A textual might appear as:
   |
   |     (outlier if any)
   |
---|----- (whisker to max: 100)
|  |     |
|  |----- (median: 76.5)
|  |
---|----- (box: IQR from 67.5 to 87.5)
   |
This format emphasizes the IQR's role in depicting the data's robust . Box plots offer benefits such as immediate of the data's via the IQR's width and straightforward detection of or s, making them ideal for comparing distributions across groups at a glance. A variation, the notched box plot, adds indented notches around the to approximate a 95% , calculated as roughly ±1.58 × IQR / √n, facilitating visual tests for differences between plots (non-overlapping notches suggest significant disparity).

Advanced Uses

IQR in Distributions

The interquartile range (IQR) exhibits distinct properties across various probability distributions, offering insights into the scale and spread of data in theoretical population settings. For the normal distribution \mathcal{N}(\mu, \sigma^2), the population IQR equals approximately $1.35\sigma, precisely $2\Phi^{-1}(0.75)\sigma \approx 1.349\sigma, where \Phi^{-1} is the of the . This interval spans the central 50% of the probability mass, from the 25th to the 75th percentiles, providing a robust measure of dispersion that aligns closely with $1.35 times the standard deviation for symmetric, bell-shaped data. In contrast, for a over the interval [a, b], the population IQR simplifies to (b - a)/2. The quartiles occur at Q_1 = a + 0.25(b - a) and Q_3 = a + 0.75(b - a), yielding an IQR that captures exactly half the total range, reflecting the equal probability density across the support. This fixed proportion highlights the IQR's sensitivity to the bounds in bounded, flat distributions, differing from its behavior in unbounded cases like the normal. For skewed distributions, such as the lognormal or , the IQR demonstrates greater robustness to extreme values in the tails compared to mean-based measures like the standard deviation, which can be disproportionately inflated by or outliers. By focusing solely on the central quartiles, the IQR mitigates the influence of heavy tails, making it a preferred scale estimator in non-symmetric settings where tail behavior distorts location-scale parameters. Asymptotically, the sample IQR converges consistently to the IQR as the sample size n increases, with its approaching via the for quantiles. Relative to the sample standard deviation, the IQR exhibits an asymptotic relative efficiency of approximately 37% under , indicating lower precision for symmetric data but superior robustness elsewhere. These properties underscore the IQR's role in distributional analysis, particularly when normality assumptions may not hold, though further diagnostics can assess fit.

Normality Assessment

The interquartile range (IQR) serves as a diagnostic for assessing whether a follows a by comparing it to the expected relationship with the deviation. For a , the IQR, defined as Q3 - , is approximately 1.349 times the deviation σ, derived from the fact that the 25th and 75th percentiles correspond to z-scores of approximately ±0.6745 under the normal curve. This leads to the normalized rule: (Q3 - ) / (2 × 0.6745 σ) ≈ 1, where significant deviations from unity suggest non-normality due to differences in central spread. A simple ratio test using the IQR involves computing the sample IQR and dividing it by the sample standard deviation s to obtain IQR / s, which should approximate 1.349 if the data are normally distributed. The procedure entails sorting the data to find Q1, Q2 (), and Q3; calculating IQR = Q3 - Q1; estimating s as the sample standard deviation; forming the ; and comparing it to 1.349 via testing, where the null assumes . For p-values, one may rely on the asymptotic of the or simulations under the null, though exact critical values depend on sample size. IQR-based assessments extend to robust measures of , such as adaptations incorporating and . Bowley's skewness, calculated as (Q1 + Q3 - 2 Q2) / IQR, quantifies using quartiles and should be near zero for symmetric data; values significantly different from zero indicate skewness and potential non-normality. Post-2000 developments, including its application in distinguishing from lognormal distributions, highlight its robustness in clinical data . Similarly, Moors' , a quantile-based measure contrasting tail probabilities to the IQR, evaluates peakedness or tail heaviness; for , it aligns with mesokurtosis (kurtosis ≈ 3 in terms), with deviations signaling excess kurtosis or platykurtosis. These IQR-integrated checks provide quick diagnostics without assuming full moment existence. Despite their utility, IQR-based tests like the simple ratio have limitations, including low power to detect non-normality in moderate to large samples compared to established methods such as the , and they may fail against specific alternatives like heavy-tailed distributions. They are best suited for preliminary, robust evaluations, particularly when outliers are present, rather than as standalone formal tests.

References

  1. [1]
    3.2 - Identifying Outliers: IQR Method | STAT 200
    Any observations that are more than 1.5 IQR below Q1 or more than 1.5 IQR above Q3 are considered outliers. This is the method that Minitab uses to identify ...
  2. [2]
    Interquartile Range and Boxplots (1 of 3) – Concepts in Statistics
    The interquartile range (IQR) is the distance between the first and third quartile marks, measuring the variability of the middle 50% of data.
  3. [3]
    Quartiles and Box Plots - Data Science Discovery
    Box plots show the inter quartile range (commonly called the IQR), a measure of the spread of the data. The IQR is the value of Q3 - Q1. The IQR tells us the ...
  4. [4]
    Interquartile Range
    Oct 5, 2001 · The interquartile range is: IQ = UPPER QUARTILE - LOWER QUARTILE. That is, it is the difference betweeen the 75th and 25th percentiles of a variable.Missing: definition | Show results with:definition
  5. [5]
    Using the interquartile range in infection prevention and control ...
    Jan 10, 2024 · The IQR represents the middle fifty percent of the data. Consequently, the IQR is less influenced by exceptional data points, commonly referred to as outliers.
  6. [6]
    [PDF] Statistics and the Physical World - University of Florida
    Jun 22, 2025 · • Interquartile Range (IQR): Distance between top (75th percentile) ... Francis Galton measured many aspects of humans, plants, and ...
  7. [7]
    Earliest Known Uses of Some of the Words of Mathematics (I)
    INTERQUARTILE RANGE is found in 1882 in Francis Galton, "Report of the Anthropometric Committee," Report of the 51st Meeting of the British Association for ...
  8. [8]
    [PDF] Galton, Francis | UGA Psychology
    However, he used the interquartile distance as his measure of variation, which would be replaced by the standard deviation in Karl Pearson's product- moment ...Missing: history | Show results with:history
  9. [9]
    Quartiles & Quantiles | Calculation, Definition & Interpretation - Scribbr
    May 20, 2022 · Quartiles are three values that split sorted data into four parts, each with an equal number of observations. Quartiles are a type of quantile.
  10. [10]
    Quartile: Definition, Finding, and Using - Statistics By Jim
    Quartiles are three values that split your dataset into quarters. They are a type of quantile that splits the data into four equal-sized groups.
  11. [11]
    1.3.3.7. Box Plot - Information Technology Laboratory
    Calculate the median and the lower and upper quartiles. Plot a symbol at the median and draw a box between the lower and upper quartiles. Calculate the ...
  12. [12]
    How to Find Quartiles in Even and Odd Length Datasets - Statology
    Dec 21, 2022 · To find quartiles, find the median, split the dataset in half, and calculate Q1 and Q3 from the lower and upper halves, excluding the median. ...
  13. [13]
    Quantile
    Hyndman and Fan (1996) in an American Statistician article evaluated nine different methods (we will refer to these as R1 through R9) for computing percentiles ...
  14. [14]
    Sample quantiles in statistical packages - Rob J Hyndman
    Nov 16, 1996 · We compare the most commonly implemented sample quantile definitions by writing them in a common notation and investigating their motivation and some of their ...
  15. [15]
    Hinge Techniques for Determining Quartiles - Peltier Tech
    Jan 10, 2013 · In the inclusionary (Tukey) approach, the hinges are the midpoints of the data halves, or 3 and 7. Inclusive definition of upper and lower ...
  16. [16]
    Full article: Quartiles in Elementary Statistics
    2017年12月1日 · In this paper, we examine the various methods and offer a suggestion for a new method which is both statistically sound and easy to apply.
  17. [17]
    Range and quartiles - Theory mathematics - Dr. Aart
    Method of Moore & McCabe​​ The lower quartile is the median of the first half excluding the median: 1, 2, 4, 5, 7, 8 so Q 1 = (4 + 5) : 2 = 4.5.缺少字词: Hyndman Fan
  18. [18]
    quantile function - RDocumentation
    One of the nine quantile algorithms discussed in Hyndman and Fan (1996), selected by type , is employed. All sample quantiles are defined as weighted averages ...
  19. [19]
    QUARTILE.INC function - Microsoft Support
    QUARTLE.INC returns the quartile of a data set, based on percentile values from 0..1, inclusive. Quartiles often are used in sales and survey data to divide ...
  20. [20]
    numpy.percentile — NumPy v2.3 Manual
    ### Summary of How `numpy.percentile` Computes Quartiles
  21. [21]
    [PDF] Calculating the Quartile (Or Why Are My Quartile Answers Different?)
    There are five methods that SAS uses to calculate the quartile, each of which can be called using various procedure options including the QNTLDEF=value option ...
  22. [22]
    Math In Society: Summary Statistics: Measures of Variation
    The IQR is calculated as the difference between the third quartile (Q3) and the first quartile (Q1). Before we can calculate the interquartile range, though, we ...
  23. [23]
    Sample Quantiles in Statistical Packages - Taylor & Francis Online
    There are many definitions for sample quantiles in statistical packages, often differing within the same package. The median-unbiased estimator is recommended.Missing: interquartile | Show results with:interquartile
  24. [24]
    None
    **Summary of Sample Quantiles from Sample Quantiles.pdf**
  25. [25]
    STAT:2010 2019 Statistical Methods and Computing Measures of ...
    Statistical Methods and. Computing ... The quartiles and the interquartile range. • The ... The IQR is considered less sensitive to out- liers than the range.
  26. [26]
    1.3.5.6. Measures of Scale - Information Technology Laboratory
    In general, for data with extreme values in the tails, the median absolute deviation or interquartile range can provide a more stable estimate of spread than ...
  27. [27]
    Measures of dispersion - PMC - PubMed Central - NIH
    The main disadvantage in using interquartile range as a measure of dispersion is that it is not amenable to mathematical manipulation. STANDARD DEVIATION.
  28. [28]
    [PDF] the range, inter- quartile range and standard deviationar charts
    Where x represents each value in the population, x is the mean value of the sample, Σ is the summation (or total), and n-1 is the number of values in the sample ...
  29. [29]
    [PDF] Lecture 36. Summarizing Data - III - Math 408 - Mathematical Statistics
    Apr 29, 2013 · Two simple robust measures of dispersion are the interquartile range (IQR) and the median absolute deviation (MAD). IQR is the difference ...
  30. [30]
    1.4 Variability
    So, the interquartile range is the distance between the 25th percentile and the 75th percentile. The interquartile range then is another measure of variability.
  31. [31]
    Variability
    The interquartile range or IQR is the range that spans the middle 50% of the data. Finding Quartiles. We previously found the median (50th percentile) for these ...
  32. [32]
    [PDF] DATA ANALYSIS, ExPLORATORY - UC Berkeley Statistics
    The collected works of John. W. Tukey: Philosophy and principles of data analysis. 1949–1964 (Vols. III & IV). London: Chapman &. Hall. McNeil, D. R. (1977).
  33. [33]
    When Tukey Meets Chauvenet: A New Boxplot Criterion for Outlier ...
    On the other hand, however, Tukey's boxplot is free of sample size, yielding the so-called “one-size-fits-all” fences for outlier detection. Although ...Missing: scholarly | Show results with:scholarly
  34. [34]
    A simple more general boxplot method for identifying outliers
    One simple way commonly employed to identify outliers is based on the concept of the boxplot and involves the use of “inner fences” and “outer fences.”Missing: scholarly limitations
  35. [35]
    Empirical Evaluation of the Relative Range for Detecting Outliers
    Jul 7, 2025 · One of the primary issues with Tukey's boxplot is that it often constructs fences (thresholds for identifying outliers) that extend too far ...
  36. [36]
    [PDF] A Review and Comparison of Methods for Detecting Outliers in ...
    Apr 26, 2006 · Most real-world data sets contain outliers that have unusually large or small values when compared with others in the data set.Missing: interquartile | Show results with:interquartile
  37. [37]
    [PDF] 40 years of boxplots
    Dec 9, 2010 · John Tukey has been credited with introducing the box and whiskers plot 1 in his book Exploratory Data. Analysis [15]. Over time, the box and ...
  38. [38]
    Visualizing samples with box plots | Nature Methods
    Jan 30, 2014 · To assist in judging differences between sample medians, a notch (Fig. 1b) can be used to show the 95% confidence interval (CI) for the median, ...<|control11|><|separator|>
  39. [39]
    [PDF] V. ESTIMATION
    The interquartile range is 2 × 0.6745, or about 1.35. The mean and standard deviation of the standard normal distribution are defined using techniques of ...Missing: sigma | Show results with:sigma
  40. [40]
    [PDF] Reference Intervals - NCSS
    In fact, if the data are normally distributed, a robust estimate of the sample standard deviation is IQR/1.35. If a distribution is very concentrated around its ...Missing: sigma | Show results with:sigma
  41. [41]
  42. [42]
    [PDF] arXiv:1405.5027v1 [math.ST] 20 May 2014
    May 20, 2014 · The asymptotic relative efficiency of the mean deviation with respect to the standard deviation is 88% at the normal distribution. In his ...
  43. [43]
    Should the Interquartile Range Divided by the Standard Deviation ...
    We discourage the use of a diagnostic for normality: the interquartile range divided by the standard deviation.
  44. [44]
    A Quantile Alternative for Kurtosis - jstor
    Recently, Moors (1986) showed that kurtosis is easily interpreted as a measure of dispersion around the two values u ? a. For this dispersion an alternative ...Missing: IQR | Show results with:IQR<|control11|><|separator|>