
compute the mean, median and mean absolute deviation of a data set and use them to compare two distributions.
Instruction
Two numbers summarize most distributions: one for the center (a typical value) and one for the spread (how much values vary). This lab builds fluency with both.
Mean and median. The mean is the sum of the values divided by how many there are; think of it as the balance point of a dot plot. The median is the middle value of the ordered data (or the mean of the two middle values when there is an even count).
Worked example. Here are daily high temperatures, in °F, for one July week in a coastal city and an inland valley city (illustrative data shaped like typical summer patterns):
Coastal: 64, 66, 65, 67, 63, 66, 64 | Inland: 88, 95, 101, 99, 92, 100, 97
Coastal mean: the sum is 455, and 455 ÷ 7 = 65°F. Inland mean: the sum is 672, and 672 ÷ 7 = 96°F. Ordered, the coastal data are 63, 64, 64, 65, 66, 66, 67, so the median is also 65. The inland data ordered are 88, 92, 95, 97, 99, 100, 101, so the median is 97.
Mean absolute deviation (MAD). To measure spread, ask: on average, how far is each value from the mean? For each value, find its distance from the mean (ignore the sign), then average the distances.
Coastal deviations from 65: −1, 1, 0, 2, −2, 1, −1. Distances: 1, 1, 0, 2, 2, 1, 1, which sum to 8. MAD = 8 ÷ 7 ≈ 1.14°F.
Inland deviations from 96: −8, −1, 5, 3, −4, 4, 1. Distances sum to 8 + 1 + 5 + 3 + 4 + 4 + 1 = 26. MAD = 26 ÷ 7 ≈ 3.71°F.
Interpretation. The inland city was about 31°F hotter on average that week, and its temperatures varied more: a typical inland day was about 3.7°F from the weekly mean, while a typical coastal day was only about 1.1°F away. A good comparison always names both center and spread, in context and with units.
Why take absolute values? The signed deviations always sum to zero, because the mean is the balance point. Check it for the coastal data: −1 + 1 + 0 + 2 − 2 + 1 − 1 = 0. Without absolute values, every data set would have an “average deviation” of 0, which tells you nothing.
Precision. The data were recorded to the nearest degree, so reporting a MAD of 1.142857°F claims accuracy the thermometer never had. One or two decimal places is plenty.
Practice. Compute the mean, median and MAD for each set of problems in the lab, first by hand and then with a spreadsheet (AVERAGE, MEDIAN and AVEDEV). Where your hand and spreadsheet answers disagree, find the error before moving on.
📖 Read for this lesson
The reading opens over the lesson; close it to come back to exactly where you were. The checks below draw on it.
Formative check
Work through these before moving on. They are not graded — they tell you whether the standard below has landed yet.
The data are 2, 4, 6, 8, 10. What is the mean absolute deviation?
For the inland temperatures, the mean is °F and the median is °F.
The signed deviations from the mean of any data set add up to zero.
Write a three-sentence comparison of the coastal and inland temperature data that names a measure of center and a measure of spread for each city, with units, and says what the difference means for someone planning outdoor work in July.
How confident are you that you can compute mean, median and MAD and use them to compare two groups?
Practice
Work these on paper or in your notebook, then open Check your answer. Aim for all of Fluency and Application; try at least one Challenge.
Printable version: this unit’s practice workbook (PDF)
Fluency
Build speed and accuracy with the core skill.
- For the data 2, 12, 21, 25, 31, 36, 39, 40: find the mean, median, range and interquartile range. (Find the quartiles as the medians of the lower and upper halves, leaving out the overall median when the count is odd.)
Check your answer
Answer: mean = 25.75; median = 28.0; range = 38; IQR = 21.0 (Q1 = 16.5, Q3 = 37.5) - For the data 18, 20, 21, 29, 32, 34, 35, 38: find the mean, median, range and interquartile range. (Find the quartiles as the medians of the lower and upper halves, leaving out the overall median when the count is odd.)
Check your answer
Answer: mean = 28.38; median = 30.5; range = 20; IQR = 14.0 (Q1 = 20.5, Q3 = 34.5) - For the data 8, 9, 15, 17, 19, 23, 40: find the mean, median, range and interquartile range. (Find the quartiles as the medians of the lower and upper halves, leaving out the overall median when the count is odd.)
Check your answer
Answer: mean = 18.71; median = 17.0; range = 32; IQR = 14.0 (Q1 = 9.0, Q3 = 23.0) - Find the mean and the mean absolute deviation of 2, 4, 6, 8, 10.
Check your answer
Answer: mean 6; MAD 2.4Average the distances from the mean. - Find the mean and the mean absolute deviation of 5, 7, 7, 9, 12.
Check your answer
Answer: mean 8; MAD 2Average the distances from the mean. - Find the mean and the mean absolute deviation of 10, 12, 15, 15, 18, 20.
Check your answer
Answer: mean 15; MAD 2.67Average the distances from the mean.
Application
Use the skill in context. Show your reasoning.
- A student’s quiz scores are 78, 85, 92, 88. What score on the fifth quiz makes the mean exactly 86?
Check your answer
Answer: 87The five scores must total 86 × 5 = 430; 430 − 343 = 87. - The inland week from Lesson 1.2 (88, 95, 101, 99, 92, 100, 97) gets an eighth day of 110°F. Find the new mean and median. Which changed more?
Check your answer
Answer: Mean 97.75°F (was 96); median 98°F (was 97). The mean changed more.The mean uses the size of every value; the median only its position. - Two students time their bike commute in Columbia for a week (minutes). Ana: 22, 24, 25, 23, 26. Ben: 15, 30, 20, 28, 32. Compare means and MADs. Who is more consistent?
Check your answer
Answer: Ana: mean 24, MAD 1.2. Ben: mean 25, MAD 6. Ana is far more consistent.Similar centers, very different spreads.
Challenge
Stretch problems. Expect to think before you write.
- The data are 3, 8, 10 and x, where x ≥ 10. Find x so that the mean equals the median.
Check your answer
Answer: x = 15For x ≥ 10 the median is (8 + 10) ÷ 2 = 9, so (21 + x) ÷ 4 = 9 and x = 15.
Review
Keep earlier skills sharp.
- Evaluate |−7| + |3 − 10|.
Check your answer
Answer: 14Both absolute values are 7. - Evaluate −4 − (−9)(2).
Check your answer
Answer: 14Multiply first: (−9)(2) = −18; then −4 − (−18) = 14.
Seven Julys: A Small Real Data Set for Mean, Median and MAD
NOAA National Centers for Environmental Information, Climate at a Glance: City Time Series — July average maximum temperature, Fresno (station USW00093193) and San Diego (station USW00023188), 1995–2025; retrieved September 23, 2026 · Public domain (works of the United States government)
Why this reading. The worked example in this lab uses temperatures “shaped like typical summer patterns.” Here are seven real ones from each of the same two cities, so your fluency practice runs on numbers a federal agency actually published. Every step of the arithmetic is shown, so you can find your own mistakes without waiting for an answer key.
The data
July average maximum temperature, in °F, for the seven most recent Julys on record at each station:
| July of | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 |
|---|---|---|---|---|---|---|---|
| Fresno | 99.0 | 99.9 | 103.3 | 100.8 | 101.8 | 105.2 | 97.0 |
| San Diego | 73.3 | 74.4 | 76.0 | 72.2 | 74.1 | 76.7 | 73.3 |
Fresno, worked
The seven values add to 707.0, so the mean is 707.0 ÷ 7 = exactly 101.0 °F. In order they are 97.0, 99.0, 99.9, 100.8, 101.8, 103.3, 105.2, so the median is the 4th value, 100.8 °F.
Deviations from the mean, in the order the table lists them: −2.0, −1.1, +2.3, −0.2, +0.8, +4.2, −4.0. They add to zero, as deviations from a mean always do. Their absolute values add to 2.0 + 1.1 + 2.3 + 0.2 + 0.8 + 4.2 + 4.0 = 14.6, so MAD = 14.6 ÷ 7 ≈ 2.09 °F.
San Diego, worked
The seven values add to 520.0, so the mean is 520.0 ÷ 7 ≈ 74.29 °F. In order: 72.2, 73.3, 73.3, 74.1, 74.4, 76.0, 76.7, so the median is 74.1 °F. The absolute deviations from 74.2857 are 0.99, 0.11, 1.71, 2.09, 0.19, 2.41, 0.99, adding to about 8.49, so MAD ≈ 1.21 °F.
Reading the comparison
Across these seven Julys Fresno ran about 26.7 °F hotter on average (101.0 − 74.29), and it also varied more: a typical Fresno July sat about 2.1 °F away from its seven-year mean, a typical San Diego July only about 1.2 °F. Both facts belong in a comparison. Giving only the centers would hide the second one.
On precision. NOAA publishes these to one decimal place. A MAD reported as 2.0857142857 °F claims an accuracy nobody has. Two decimal places at the very most, and one is usually honest enough.
On averaging an average. Every value here is already an average — of thirty-one daily maximums. Averaging seven of them gives each July equal weight, which is right when the question is about Julys. It would be the wrong move if the question were about days, because then a month with more days should count for more.
Sources: NOAA NCEI, Climate at a Glance: City Time Series (Fresno) (ncei.noaa.gov); NOAA NCEI, Climate at a Glance: City Time Series (San Diego) (ncei.noaa.gov)