Making a frequency table is not difficult, once you understand the concept behind what you are doing. The point of making a frequency table is to take a large group of data and break it down into categories, buckets or class intervals so that it is easier to understand and analyze.
By sorting, and then classifying data into categories, a large amount of data can be analyzed more easily.
Let's take a situation such as age groups of an employer.
We will use 10 inputs to this 'how to make a frequency table', so you can visualize it as we go along.
The numbers we will use are : 20, 27, 55, 66, 53, 42, 37, 59, 51, and 44.
Step 1: Sort data
Take the data and sort it, so that the data is in numerical order. In our case, the data would look like
Microsoft Excel can be used to easily sort data in frequency distribution table, in alphanumerical sequence.
Note we still have the same 10 inputs, however they are now sorted in ascending, numerical order.
Step 2: Create buckets or class intervals
Our point in establishing a frequency table is to analyze the data, but first we have to create logical buckets for the data to be reviewed. We want the data to accurately reflect the appropriate buckets and we do this objectively by first defining the bucket sizes, or frequency distribution.
It is a good idea to keep the your data buckets to a manageable size, usually 5 categories is a good start.
In our case, we have a range of numbers basically between 0 - 100. If we divide 100 by 5, we come up with a range of 20 integers per bucket or class interval. The bin size in our case is 5, as we have 5 class interval categories.
Logically we can assume that each of our buckets would have to have 20 numbers, sequentially to make up a range or category with a range from 1 - 100.
Step 3: Count frequency in each class interval or bucket
Now that we have decided what our class interval or category ranges are, next we have a task to count how many of our data elements or pieces of data fit into each category.
In our case, we used excel to find:
41 -60 6
61- 80 1
The distribution would look like this:
What can an employer do with this information?
They can compare the categories to different costs such as insurance rates, education costs, and overtime based upon certain assumptions that would be attributed to each class interval or class category.