Mean for Grouped Data
You already know how to calculate the mean for individual data, right? Just sum up all the values and divide by the number of data points.
But what if the data is presented in groups or intervals, like in a frequency distribution table? For example, test scores grouped into 70-79, 80-89, 90-100.
When data is grouped, we don't know the exact value of each data point within that group. For instance, if there are 5 students in the 70-79 group, we don't know if their scores are exactly 70, 72, 75, or some other value within that range.
Using the Class Midpoint
Since we don't know the exact values, we use an assumption or approximation. We assume that all data points within a group are represented by the midpoint of that group (class interval).
The class midpoint (often symbolized as ) is calculated as:
Formula for Mean of Grouped Data
Once we have the midpoint for each class, we can calculate the mean of the grouped data using the formula:
Where:
- = Mean of the grouped data
- = Frequency of the -th class (how many data points are in that group)
- = Midpoint of the -th class
- = Sum of the products of the frequency and midpoint for each class
- = Sum of all frequencies (equal to the total number of data points, )
Example: Average Shoe Size
Consider the grouped data for shoe sales at Store A:
Shoe Size (Class Interval) | Frequency () |
---|---|
37-39 | 2 |
40-42 | 11 |
43-45 | 16 |
46-48 | 1 |
Total |
Steps to calculate the Mean:
-
Find the Midpoint () for each class:
- Class 37-39:
- Class 40-42:
- Class 43-45:
- Class 46-48:
-
Multiply Frequency by Midpoint () for each class:
- Class 37-39:
- Class 40-42:
- Class 43-45:
- Class 46-48:
-
Sum all the products ():
-
Sum all frequencies ():
-
Calculate the Mean ():
Therefore, the average shoe size sold at Store A is 42.6.
Remember, this result is an estimate of the mean because we use midpoints to represent the data within each group. However, this is the standard and most common way to calculate the mean for grouped data.