Measures of Central Tendency MDM4U
It is often convenient to use a central value to summarize a set of data. Howerver, there are several
different ways to find values around which a set of data tends to cluster. You have probably been
introduced to 3 of them already…
Mean: The mean is defined as the sum of all the values of a variable, divided by the number of values.
There is an important difference between the means of a sample (say one classroom in a school) and the
mean of a population (the whole school). We can write them in sigma notation:
Median: The median is the central value of the data, after they are ranked. In the case of two central
values, the median is the average of these two values.
Example: Find the mean and median for these data sets…
a) {2, 5, 4, 7, 8, 4, 6, 3} b) { 3, 4, 2, 5, 9, 6, 5, 5, 4 }
Mode: The mode is the most frequently occuring data value (or values). A set of data can have no
mode, 1 mode, or several modes. For example, find the mode for the following sets of data…
a) {1, 2, 3, 4, 4, 5} b) {1, 2, 3, 3, 4, 4, 5}
c) {1, 2, 3, 4, 5, 6} d) {1, 1, 2, 2, 3, 3}
Outliers: An outlier is a data point that is quite different from the other points in the data set. Later on,
we will have a formal method to identify outliers. For now, calculate the mean and median of the
following two data sets (one with an obvious outlier removed).
a) {1, 2, 3, 3, 4, 12} b) {1, 2, 3, 3, 4}
Clearly, outliers in small data sets affect the ____________ the most.
Measures of Central Tendency MDM4U
Visual Illustration of outliers:
Here are some helpful guidelines to use when analyzing data with outliers.
If the data is roughly symmetric use either the mean or median
If the data set is small, and there appear to be outliers, use the median
If the data is not numeric (qualitative) or if the frequency is the most critical, then use the mode
Grouped Data and Weighted Means Frequency, Midpoint
Age fxm
f (age), m
Sometimes you do not have the original data, only a
16 – 20 10
summary showing the data grouped into intervals. In
this case you can use the midpoint of each interval to 21 – 25 18
estimate the mean: 26 – 30 12
31 – 35 8
36 - 40 2
Total
Estimate the mean and median age for the following
grouped data:
Measures of Central Tendency MDM4U
Weighted Means: Sometimes certain data is more
Category Weight, w Mark, x w·x
important than other data. For example, when
KU 30 80
computing an overall mark, Knowledge is weighted
more heavily than other categories. App 25 70
Calculating a weighted average is a lot like calculating Comm 25 70
the mean for grouped data. Instead of frequencies, TIPS 20 90
we have weights:
Total -----
Example: Bort’s data management exam is worth 20% of his final mark.
a) If Bort had a 70% going into the exam, and b) If Bort had a 70% going into the exam, is it
got 80% on the exam, calculate his final mark. mathematically possible to raise it to 75%?
Calculate the required exam score to find out.
