Saved

Press the star next to a tool's name to save it.

All my tools

Descriptive Statistics Calculator

Use this descriptive statistics calculator to find the mean, median, mode, quartiles, five-number summary, box plot outliers, standard deviation and coefficient of variation.

Restored your last values ·

Paste or type your numbers. You get the count, sum, mean, median, mode, range, quartiles, the five-number summary, the box plot fences and outliers, the standard deviation and variance, and the coefficient of variation. Choose the quartile method that your course or software uses.

Everything is worked out in your browser. Nothing you type is sent anywhere.

–

–

Enter your data, then press Calculate.

A descriptive statistics calculator sums up a list of numbers in one go. Paste your data, and you get the count, sum, mean, median and mode, the range, the quartiles and the five-number summary, the fences and outliers of a box plot, the sample and population standard deviation and variance, and the coefficient of variation. It also covers what separate tools call a five number summary calculator, a box plot calculator and a coefficient of variation calculator. It runs in your browser.

How to use the descriptive statistics calculator

  1. Type or paste your data, with the values separated by spaces, commas or new lines.
  2. Choose the quartile method.
  3. Press Calculate.

The five-number summary

The Wikipedia article on the five-number summary describes it as a set of five sample percentiles: the minimum, the lower or first quartile, the median, the upper or third quartile and the maximum.[1] Its example uses the number of moons of the planets, 0, 0, 1, 2, 63, 61, 27 and 13. Sorted, they are 0, 0, 1, 2, 13, 27, 61 and 63. The median is (2 + 13) ÷ 2 = 7.5. The lower quartile is the median of the lower half, 0, 0, 1 and 2, which is 0.5, and the upper quartile is the median of the upper half, 13, 27, 61 and 63, which is 44. The summary is 0, 0.5, 7.5, 44 and 63.[1] The default method of the calculator, the median of each half, gives exactly this.

Why quartiles differ

The page points out that the summary function of the R language gives 0.75 and 35.5 for the quartiles of the same data, which is a different method from the five-number function that gives 0.5 and 44.[1] The calculator offers three methods. The median of the halves is the textbook method, and when the number of values is odd, it leaves out the middle value. The inclusive method interpolates at the rank p(n − 1) + 1, as Excel's QUARTILE.INC does, and gives 0.75 and 35.5 here. The exclusive method uses the rank p(n + 1), as Excel's QUARTILE.EXC does, and gives 0.25 and 52.5.

Box plot fences and outliers

The article on box plots explains that a box runs from the first to the third quartile, with the median marked, and that whiskers reach to the most extreme data points that lie within 1.5 times the interquartile range of the box. Points beyond the whiskers are drawn as outliers. The range is measured up from the third quartile and down from the first, and the whiskers end on data points, so they can be of unequal length.[2] The page's example has 24 hourly temperatures with a first quartile of 66, a median of 70 and a third quartile of 75. The IQR is 9, 1.5 IQR is 13.5, and the fences are 52.5 and 88.5. Its temperatures run from 57 to 81, so there are no outliers.[2] The calculator gives the fences, the ends of the whiskers and the list of outliers for your data.

Mean, median and mode

The mean is the sum divided by the count, and it is pulled by extreme values. The median is the middle value of the sorted list, or the average of the two middle ones, and it is not much changed by extremes. The mode is the value that occurs most often. If several values tie, the calculator lists them all, and if every value is different, it says that there is no mode. For the moons data the mean is 20.875, much higher than the median of 7.5, because of the two large values.

Standard deviation and variance

The sample standard deviation divides the sum of squared deviations from the mean by n − 1, and the population one divides by n. Use the sample form when your data is a sample of a larger group, and the population form when it contains every case. The variance is the square of the standard deviation. For the values 90, 100 and 110, the sample standard deviation is 10 and the population standard deviation is 8.16.

Coefficient of variation

The article on the coefficient of variation defines it as the ratio of the standard deviation to the mean, often given as a percentage, and estimated from a sample as s ÷ x̄.[3] For 90, 100 and 110, it is 10 ÷ 100 = 0.1, or 10 percent with the sample standard deviation, and 0.0816 with the population one. For the list 1, 5, 6, 8, 10, 40, 65 and 88, the mean is 27.9, the sample standard deviation is 32.9 and the coefficient is 1.18.[3] The page stresses that it should be used only for data on a scale with a meaningful zero. For temperatures of 0, 10, 20, 30 and 40 in Celsius it gives 79 percent, but the same temperatures in kelvin give only 5.39 percent, so the number has no meaning for such data. It also grows without limit as the mean nears zero.[3]

More measures

The calculator also shows the standard error of the mean, which is the sample standard deviation divided by the square root of n, and the relative standard error, which is that error as a percentage of the mean. It gives the sum of squares, both raw and about the mean, the midrange, the average of the smallest and the largest value, and two absolute deviations: the mean absolute deviation around the mean, and the median absolute deviation around the median. The skewness is the adjusted Fisher–Pearson coefficient, which is positive when the tail runs to the right. These are standard definitions that we apply ourselves and the pages that we cite do not cover them.

Using the results

The five-number summary and the box plot fences are the basis of a quick look at the shape of the data. If the median is far from the middle of the box, or one whisker is much longer than the other, the data is skewed. Values beyond the fences deserve a check: they may be errors or truly unusual cases. The coefficient of variation lets you compare the spread of data measured in different units, such as the variation of heights and of weights.

Common mistakes

  • Mixing quartile methods. State the method that you used.
  • Using the population formula for a sample. A sample uses n − 1.
  • Applying the coefficient of variation to temperatures. It needs a true zero.
  • Dropping outliers without a reason. Check them first.

What next

Use this often? Add Descriptive to your Home screen.

Frequently asked questions

What is a descriptive statistics calculator?

A tool that sums up a list of numbers with the mean, median, mode, spread, quartiles and other measures.

What is the five-number summary?

The minimum, first quartile, median, third quartile and maximum of the data.

How are box plot outliers found?

A value is an outlier if it is below Q1 − 1.5 × IQR or above Q3 + 1.5 × IQR.

What is the coefficient of variation?

The standard deviation divided by the mean, often given as a percentage. It is meaningful only for data with a true zero.

Why do quartiles differ between programs?

There are several methods. The median-of-halves, inclusive and exclusive methods give different answers for the same data.

What went wrong?

We only receive the reason you pick, never what you typed into the tool.

Thanks for your feedback.

More Math Tools