Range and mean deviation · Mathematics Class 11–12 | StemPy Lab
Course 17.1·Lesson 2 of 3
Range and mean deviation
Two data sets can have the same mean and look nothing alike. The range gives the full width of the data in one subtraction. The mean deviation gives the average distance of the values from a centre, and it uses every value.
about 25 min1 simulation1 practice question1 Python program5 questions to check yourself
This lesson is free to read. Enroll free to keep your place and take the tests.
Lesson 2 of 3Show all lessonsHide
Try the code and the simulations beside the lesson.
What you will be able to do
find the range and the coefficient of range;
find the mean deviation about the mean or about the median, for a list, a frequency table and grouped data;
explain why the deviations are taken without their sign, and why the median gives the smallest mean deviation.
The same average, a different story
Two machines fill bags of rice, each meant to hold 500g. Machine A fills five bags with 498,499,500,501 and 502g. Machine B fills five bags with 480,490,500,510 and 520g. Both machines have a mean of 500g. Yet nobody would buy rice from machine B with the same trust. The mean cannot see this difference. We need a number for the spread, also called the dispersion, of the data.
The range
The simplest measure is the range:
range=largest value−smallest value.
Machine A has range 502−498=4g. Machine B has range 520−480=40g. The range is quick, and it has the same unit as the data. But it uses only two values, so one odd reading changes it a lot.
To compare two data sets in different units, use the coefficient of range:
largest+smallestlargest−smallest.
It has no unit. For machine A it is 10004=0.004 and for machine B it is 100040=0.04.
Deviations from a centre
A deviation is the distance of a value from a centre a, written x−a. It is positive for a value above the centre and negative below it. Suppose we take the mean as the centre. Then the deviations always add up to zero, because
∑(x−xˉ)=∑x−nxˉ=0.
So the sum of the deviations says nothing. We remove the sign by taking the absolute value, ∣x−a∣, which is the distance without direction.
The mean deviation
The mean deviation about a centre a is the mean of the distances:
MD(a)=n∑∣x−a∣.
For a frequency table, and for grouped data with the class marks as x,
MD(a)=N∑f∣x−a∣.
The centre is usually the mean or the median. Say which one: the mean deviation about the mean and the mean deviation about the median are different numbers.
For machine A the distances from the mean 500 are 2,1,0,1,2, so MD=56=1.2g. For machine B they are 20,10,0,10,20, so MD=560=12g. Now the difference is clear: machine B misses by ten times as much.
A-Level, IB and AP courses do not use the mean deviation. They use the standard deviation and the interquartile range, which come next. The Indian syllabus asks for all of them.
The curve in the simulation shows a fact worth remembering: the mean deviation is smallest when the centre is the median. The mean gives a slightly larger value. This is why a question that says "about the median" has an answer no larger than "about the mean", for a list of values.
Coefficient of mean deviation
To compare spreads in different units, divide by the centre:
coefficient of mean deviation=aMD(a).
It is a pure number. Machine B has 50012=0.024.
Two small number lines side by side, both showing the five readings 2, 4, 6, 9 and 14 as dots. On the left a red marker at the mean 7 has horizontal bars from each dot to the marker, of lengths 5, 3, 1, 2 and 7. On the right a red marker at the median 6 has bars of lengths 4, 2, 0, 3 and 8. The titles give the mean deviations 3.6 and 3.4.
A worked example with grouped data
Use the marks of 50 students from the last lesson, with class marks 5,15,25,35,45,55 and frequencies 4,8,15,10,7,6. The mean is 30.2.
The distances. From 30.2 the class marks are 25.2,15.2,5.2,4.8,14.8,24.8 away.
Multiply by the frequencies.4×25.2=100.8, then 121.6, 78, 48, 103.6 and 148.8.
Add and divide. The total is 600.8. So MD=50600.8=12.016 marks.
The coefficient.30.212.016=0.398.
Practise with new numbers
Try it in Python
The program finds the mean deviation of the five readings in the simulation about the mean, about the median, and about several other centres.
Common mistakes
Dropping the absolute value. Without it the deviations from the mean add up to zero.
Using the wrong centre. Read whether the question says about the mean or about the median.
Dividing by the number of classes. For a frequency table divide by N=∑f.
Forgetting the frequencies. In a frequency table each distance is multiplied by its frequency.
Remember these
Range = largest − smallest. Coefficient of range =largest+smallestlargest−smallest.
MD(a)=N∑f∣x−a∣, about the mean or the median.
The sum of the deviations from the mean is zero.
The mean deviation is smallest about the median.
Check yourself
Try each one on your own first. If you are stuck, open a hint. Then check with Show the answer.
Find the range and the coefficient of range of 12,7,20,15,9.
Find the mean deviation about the mean of 2,5,9,12,17.
Show that the sum of the deviations of n values from their mean is zero.
The value 2 occurs three times, 4 four times and 6 three times. Find the mean deviation about the mean.
A data set has median 40 and mean deviation about the median 6. Find the coefficient of mean deviation.
References
OpenStax, Introductory Statistics, Chapter 2, section on measures of the spread of the data.
NCERT, Mathematics for Class XI, Chapter 13 (Statistics), sections on the range and the mean deviation.
Enroll free in Centre and Spread of Data
Every lesson is open to read. Enrolling also lets you:
Mark lessons done and carry on where you stopped.
Take the tests of this lesson and its course.
Count the course towards the certificate for its chapter.