Learning Outcomes
- Compare the characteristics of two data sets graphically
Salary data from two companies is presented below, Company A and Company B, both in the same field and geographic region. We want to compare the salaries by looking at graphical representations of the data.
Salaried Employees: Company A
68340 | 87282 | 103802 | 128863 | 140085 | 162300 | 177109 |
70138 | 90553 | 106562 | 128933 | 147419 | 168676 | 180174 |
71417 | 95226 | 120701 | 130780 | 149514 | 169409 | 180221 |
71867 | 97042 | 123313 | 136204 | 152008 | 170031 | 185837 |
84675 | 100531 | 125614 | 138920 | 155032 | 175118 | 189320 |
Salaried Employees: Company B
35472 | 43467 | 53624 | 65096 | 72290 | 110351 | 124732 |
36983 | 46652 | 57946 | 66235 | 75279 | 117574 | 228920 |
38382 | 49655 | 59096 | 69721 | 107368 | 118810 | 245427 |
41674 | 53231 | 59709 | 71289 | 108236 | 119112 | 275024 |
43256 | 53506 | 61724 | 72211 | 109472 | 124678 | 293012 |
Hands-on Spreadsheet: Explore the Data
Step 1: Store the data
- Type or copy the data into a new spreadsheet. Title the tab Employee Salaries. Place the columns of data side by side in column A and column B.
- Obtain descriptive statistics for each company’s data.
- Analyze the descriptive statistics and compare the companies’ data.
Solution
Step 2: Create a box and whisker plot with both data series on the same graph
- Select both columns of data together with their labels.
- Click on Insert then Box and Whisker. You should see both sets of data appear as parallel box plots on the graph in different colors. Click to select it.
- Click the plus sign next to the chart. Click to select Legend. The data column labels should appear at the top under the Chart Title. You can now delete the Chart Title.
Step 3. Create a scatter plot with both data series on the same graph
- Follow the same steps as in Step 2 above, except this time choose Scatter Plot instead of Box and Whiskers.
Step 4: Analyze the data
As we saw in the descriptive statistics, Company A has a tighter distribution of salaries about its center. Company B possesses extremes at both ends of salary range. The salaries in B are persistently and substantially lower than A’s are with the notable exception of four outliers at the top end. These are pulling the mean of B far to the right of the median. With B’s median salary at $69,721 and A’s at $130,780, it is clear that the salary distribution at company A is more equitable than at company B. A has the higher starting salary, and higher salaries overall than all but the four outliers at company B.