CalcTrace

Statistics Calculator

Paste a list of numbers to get a full descriptive summary: count, sum, mean, median, mode, range, quartiles, interquartile range, variance, standard deviation and skewness, with outliers flagged by the 1.5 × IQR rule and drawn on a box plot.

Last updated .

Your data

Separate the numbers with commas, spaces or new lines. A comma always starts a new number, so type 1250, not 1,250.

Quartile method

Summary

Mean

–

–Count (n)
–Sum
–Median
–Mode
–Minimum
–Maximum
–Range
–Interquartile range

Quartiles and outliersValue
Lower quartile (Q1)–
Upper quartile (Q3)–
Lower fence (Q1 − 1.5 × IQR)–
Upper fence (Q3 + 1.5 × IQR)–
Outliers–
MeasureSample (n − 1)Population (n)
Variance––
Standard deviation––
Skewness––

Show the working

    What each figure means and how it is worked out

    A descriptive summary answers three questions about a data set: where its centre is, how spread out it is, and what shape it has. In the formulas below, x stands for each value in turn, n is the number of values, Σ means “add up for every value” and x̄ is the mean.

    Mean: x̄ = Σx ÷ n     Range = maximum − minimum

    Interquartile range: IQR = Q3 − Q1

    Outlier fences: lower = Q1 − 1.5 × IQR     upper = Q3 + 1.5 × IQR

    Sample variance: s² = Σ(x − x̄)² ÷ (n − 1)     Population variance: σ² = Σ(x − x̄)² ÷ n

    Skewness (population): g = [Σ(x − x̄)³ ÷ n] ÷ σ³     Skewness (sample): G = g × √(n(n − 1)) ÷ (n − 2)

    The median is the middle value of the sorted data, or the average of the middle two when n is even. The mode is the value that occurs most often. Q1 and Q3 are the lower and upper quartiles, the points a quarter and three-quarters of the way through the sorted data. The standard deviation is the square root of the variance; s is the sample version and σ the population version. Any value outside the two fences is flagged as an outlier.

    The quartile method used

    There is no single agreed definition of a quartile, and different tools give slightly different answers for the same data. This calculator offers two and tells you which is in use:

    Worked example by hand

    Ten delivery times in minutes: 12, 15, 11, 18, 14, 15, 22, 13, 16, 41.

    1. Sort. 11, 12, 13, 14, 15, 15, 16, 18, 22, 41.
    2. Mean. The values add up to 177, so the mean is 177 ÷ 10 = 17.7.
    3. Median. With ten values, the middle two are the 5th and 6th, both 15, so the median is 15.
    4. Mode and range. Only 15 appears twice, so it is the mode. The range is 41 − 11 = 30.
    5. Quartiles. The lower half is 11, 12, 13, 14, 15, with median 13, so Q1 = 13. The upper half is 15, 16, 18, 22, 41, with median 18, so Q3 = 18. IQR = 18 − 13 = 5.
    6. Fences. 1.5 × 5 = 7.5. Lower fence = 13 − 7.5 = 5.5. Upper fence = 18 + 7.5 = 25.5. The value 41 is above the upper fence, so it is an outlier.
    7. Variance and standard deviation. The squared distances from the mean add up to 692.1. Sample variance = 692.1 ÷ 9 = 76.9 and s = √76.9 = 8.77. Population variance = 692.1 ÷ 10 = 69.21 and σ = 8.32.
    8. Skewness. The sample skewness is 2.48, strongly positive, because the one slow delivery stretches the right-hand tail.

    With the interpolated method the quartiles for the same data are Q1 = 13.25 and Q3 = 17.5. Neither answer is wrong; they are different conventions, and the gap between them shrinks as the data set grows.

    Reading the summary

    Compare the mean with the median first

    In the example the mean (17.7) is above the median (15), and nine of the ten values are at or below 22. That gap is the signature of right-skewed data. Take away the 41 and the mean drops to 15.11 while the sample standard deviation falls from 8.77 to 3.33. For skewed data, report the median and IQR; for roughly symmetric data, the mean and standard deviation carry more information.

    An outlier is a question, not a verdict

    The 1.5 × IQR rule is a convention for flagging values worth a second look. A flagged value may be a typing error, a faulty measurement, or a perfectly real observation that happens to be the most interesting one in the set. Never delete a value only because a rule flagged it; find out why it is there. In heavily skewed data such as incomes, the rule will flag many legitimate values.

    Reading the box plot

    The box runs from Q1 to Q3, so it holds the middle half of the data, and the line inside it is the median. The whiskers reach to the smallest and largest values that are not outliers, and each outlier is drawn as its own circle. A median near one end of the box, or one whisker much longer than the other, shows skew at a glance.

    Skewness needs a reasonable amount of data

    A skewness near 0 suggests symmetry, a positive value a longer right tail, and a negative value a longer left tail. As a rough guide, values beyond ±1 indicate strong skew. With fewer than about 20 values the figure is unstable, since one observation can swing it widely, as the example shows. The sample version needs at least three values.

    Sample or population

    Use the n − 1 column when your numbers are a sample from something larger, which is the usual case, and the n column when they are the complete group. The standard deviation calculator explains the difference in detail and lists each value’s deviation from the mean.