How it works
- Mean: add the values and divide by how many there are.
- Median: sort the values and take the middle one; with an even count, average the two middle values.
- Mode: the value that appears most often. There can be more than one, or none if every value appears once.
- Range: largest value minus smallest.
The median is not pulled by extreme values the way the mean is, which is why it is often used for incomes and house prices.
Worked example
Data: 13, 18, 13, 14, 13, 16, 14, 21, 13. Sorted: 13, 13, 13, 13, 14, 14, 16, 18, 21. Mean = 135 ÷ 9 = 15. Median = 14 (the 5th value). Mode = 13 (four times). Range = 21 − 13 = 8.
How much can one outlier move the mean?
Seven homes on a street sold for 42, 45, 47, 49, 51, 52 and 250 (in $1,000s). The total is 536, so the mean is 536 ÷ 7 ≈ 76.57. The median is 49. Six of the seven prices sit below the mean, so it does not describe a typical home.
Remove the 250 and the mean drops to 286 ÷ 6 ≈ 47.67, while the median only moves from 49 to (47 + 49) ÷ 2 = 48. The mean is pulled toward the long tail, and the median gives a better center when the data have extreme values.
A data set with two modes
Take 3, 7, 7, 2, 9, 10, 7, 2, 2. Sorted, it is 2, 2, 2, 3, 7, 7, 7, 9, 10. Both 2 and 7 appear three times, so the set is bimodal. The calculator lists both values in the Mode row. The mean is 49 ÷ 9 ≈ 5.444, the median is 7 and the range is 10 − 2 = 8. You can separate values with commas, spaces, semicolons or new lines.
How do I use a frequency table?
Suppose a quiz score of 1 appears 2 times, 2 appears 5 times and 3 appears 3 times. Either type each value as often as it occurs (1 1 2 2 2 2 2 3 3 3) or use Σ(f × x) ÷ Σf:
(1 × 2 + 2 × 5 + 3 × 3) ÷ 10 = 21 ÷ 10 = 2.1
The median is the average of the 5th and 6th values, (2 + 2) ÷ 2 = 2, and the mode is 2.
Weighted mean for course grades
If the final exam counts 50%, coursework 30% and quizzes 20%, multiply each score by its weight. Scores of 90, 80 and 70 give 0.5 × 90 + 0.3 × 80 + 0.2 × 70 = 83. The plain mean of the three scores is 80. This calculator gives every value equal weight, so work weighted grades by hand.
Midrange and trimmed mean
The midrange is (smallest + largest) ÷ 2. For the worked example on this page, with values from 13 to 21, it is (13 + 21) ÷ 2 = 17. It depends on only two values, so it is not robust. A trimmed mean drops a small share of values from each end, often 5%, before averaging.
Common mistakes
- Taking the middle of the unsorted list as the median.
- Using one middle value when the count is even.
- Quoting only the mean when a few values are extreme. The median is the safer summary then.
- Trying to average categories. For colors or brands, only the mode makes sense.
Tips
- Always sort before finding the median.
- A data set can have two modes (bimodal) or no mode at all.
- Range is quick but sensitive to outliers; the standard deviation uses every value.
Questions
What if there is no mode?
If every value appears only once, there is no mode, and the calculator says so. If two or more values tie for the most appearances, each of them is a mode: 1, 1, 2, 2 has the modes 1 and 2.
How do I find the median of an even number of values?
Average the two middle values. For 4, 8, 15, 16, 23, 42 that is (15 + 16) ÷ 2 = 15.5.
Which average should I use?
The mean uses every value; the median resists outliers; the mode suits categories and the most common value.
What is a trick to remember mean, median and mode?
Median sounds like medium, the middle value. Mode and most start with the same letters, so the mode is the most common value. The mean is the average you calculate.
What is the range in statistics?
The range is the largest value minus the smallest. It uses only those two extreme values, so a single outlier can change it a lot.
How do I find the mean from a frequency table?
Multiply each value by its frequency, add the results, and divide by the total frequency. For 1 (×2), 2 (×5) and 3 (×3) the mean is 21 ÷ 10 = 2.1.
Sources
- NIST/SEMATECH e-Handbook of Statistical Methods, §1.3.5.1 Measures of Location. Definitions of mean, median and mode; effect of skewness and extreme values; trimmed mean and mid-range. Checked 22 November 2026.
- NIST/SEMATECH e-Handbook of Statistical Methods, §1.3.5.6 Measures of Scale. Definition of the range. Checked 22 November 2026.