In this post
One thing that you may have noticed in this lesson is the class boundaries for some of the groups. In a previous post we learnt that each boundary should have individual values so that data cannot be put into two categories, but here we have used categories such as 0 – 60 and 60 – 90. This is because the data is known as continuous and a value will never be allowed to go into both groups. This is because, even though a value may be 60 minutes, this has really been rounded. A true time will always be either a little bit more or a little bit less than 60 minutes.
Alternative notation for grouped frequency
To avoid any confusion we can instead use different notation in these problems. By using x to represent the specific value we can make use of inequalities for the groups so that we are not leaving any groups ambiguous.
The use of < and > can help us to show that we are looking at a group where the values are less than or more than some value and the symbols ≤ and ≥ will tell us that the frequency includes values that are equal to the value too.
Example
Change the following frequency table so that the groups use inequalities:
| Weight of package (kg) | Frequency |
|---|---|
| 0 – 10 | 47 |
| 10 – 20 | 29 |
| 20 – 30 | 18 |
| 30 – 40 | 11 |
| 40 – 50 | 3 |
We must alter the groups slightly so that if we had a package that is exactly 10kg then we would know which it would be counted in. At the moment a package like this could be in either the first or second group. Inserting inequalities and to represent the individual weight we can have:
This table has then eliminated any ambiguity and enabled us to categorise a package that is exactly on the weight of 10kg, 20kg, 30kg etc.
| Time | 0 – 60 | 60 – 90 | 90 – 120 | 120 – 180 |
|---|---|---|---|---|
| Frequency | 5 | 11 | 29 | 12 |
| Cumulative Freq | 5 | 16 | 45 | 57 |
