User manual SPSS BRIEF GUIDE 11.5

[. . . ] SPSS 11. 5 Brief Guide ® For more information about SPSS® software products, please visit our Web site at http://www. spss. com or contact SPSS Inc. 233 South Wacker Drive, 11th Floor Chicago, IL 60606-6412 Tel: (312) 651-3000 Fax: (312) 651-3668 SPSS is a registered trademark and the other product names are the trademarks of SPSS Inc. No material describing such software may be produced or distributed without the written permission of the owners of the trademark and license rights in the software and the copyrights in the published materials. The SOFTWARE and documentation are provided with RESTRICTED RIGHTS. [. . . ] Data points In Figure 8. 1, you can see that most of the females in the data set have completed 12 years of education. Males, as the chart shows, have a greater spread in education levels. More than half have some level of college education, and a small number of males have completed graduate work. As this 2-D area chart illustrates, it is difficult to see the complete area chart for females since it is clustered behind the chart for males. Later in this chapter, you will learn how to create both paneled and 3-D area charts. These types of charts will help you to see all aspects of your data and to determine which is the best view. To create an area chart, from the menus choose: Graphs Interactive Area. . . This opens the Create Area Chart dialog box. Click Reset to restore all of the default settings. Drag Educational Level to the horizontal axis. Also drag Gender to Legend Variables Color, as shown in Figure 8. 2. Tutorial: 3-D Charts, Panels, and More Interactive Chart Features 73 Figure 8. 2 Create Area Chart dialog box The areas will show the distribution of education levels for male and female employees. Gender will be differentiated by color. The areas will be clustered rather than stacked. Click OK. Figure 8. 3 Area chart of Education Level by Gender Most female employees have 12 years of education. The largest number of males have at least 15. 74 Chapter 8 In Figure 8. 3, the area charts are clustered. This means that one area chart is placed behind the other. To compare educational levels by gender more easily, you can stack the area charts. Creating a Stacked Chart Another way to compare categories is by stacking the area charts. Double-click to activate the chart. Click the Assign Graph Variables tool dialog box. Figure 8. 4 Stacked area chart Double-click here to edit color fills for an area. to open the Assign Graph Variables From the Cluster drop-down list, choose Stack. You can now see that a number of female employees have some level of college education. In stacked charts, the top of the category for males forms the base of the category for females. Stacked charts emphasize the sum of the categories and the flow along the independent axis. However, in this type of chart, specific values of individual categories cannot be easily determined. Separating the Chart into Panels for Categories Suppose you want to better compare the educational levels for males and females. One way to do this is to use panels for the categories of the variable gender. Click the Assign Graph Variables tool Variables dialog box. to open the Assign Graph Tutorial: 3-D Charts, Panels, and More Interactive Chart Features 75 Drag Gender from the Legend list to the Panel Variables list, as shown in Figure 8. 5. Figure 8. 5 Assign Graph Variables dialog box One panel will be created for each gender. This produces a panel for each gender, as shown in Figure 8. 6. Figure 8. 6 Panels for male and female By looking at the Female panel, you can now see that there are at least 25 females with several years of college education. In 2-D clustered charts, you could not see this part of the data set because it was hidden behind the area for males. In these side-by-side panels, you can compare the gender differences more easily. 76 Chapter 8 Comparing Categories in Three Dimensions Another way to compare categories is by adding a third dimension. In the Assign Graph Variables dialog box, select 3-D Coordinate from the drop-down list. Notice that another axis target is added to the dialog box. Drag Minority Classification to the new axis. Drag Gender from the Panel Variables list to Legend Variable Color. The 3-D area chart is shown in Figure 8. 7, along with the 3-D tool palette. Figure 8. 7 3-D area chart To change the lighting, click the light icon in the 3-D tool palette. To rotate the chart horizontally, drag the dial in the 3-D tool palette. This 3-D chart compares the differences in education by gender and minority status. You can see that nonminority males have the most education, while minority females have the least. The area charts here are clustered by minority classification. Tutorial: 3-D Charts, Panels, and More Interactive Chart Features 77 Since it is difficult to see the nonminority female category, you can rotate the chart using the 3-D tools. [. . . ] Each chart is displayed in a separate window. To modify the chart: Double-click the chart in the Viewer. This opens a Chart Editor window containing the scatterplot, as shown in Figure B. 4, with the Chart Editor menu bar and toolbar displayed. Figure B. 4 Scatterplot in a chart window Chart Editor menu bar and toolbar Using Point Selection Mode to Identify Points Examining your scatterplot, you notice one person whose salary has increased from roughly $30, 000 to more that $100, 000 (as indicated in Figure B. 5). To find out more about this individual, you can use point selection mode. Tutorial: Creating and Modifying a Standard Scatterplot 149 Figure B. 5 Point selection mode in the chart window With a boxplot or scatterplot in the active chart window, click . The cursor changes to , which indicates that point selection is on. [. . . ]