Graziano & Raulin
Research Methods (9th edition)
Independent Samples t-test
For this analysis, we will compare the income level of males and females in our sample of 24 participants from Table 5.2. We begin by starting the SPSS for Windows program and selecting the option to open an existing file, which gives us this screen. We select the file Table_5-2 and open it, which gives us this screen.
To compute a simple t-test, we select the Analyze Menu, the Compare Means submenu, and the Independent Samples t-test option, which will give us this screen. We move the income variable to the box labeled Test variables and move the sex variable to the box labeled Grouping variable. We then click the Define Groups button and define Group 1 as "M" and Group 2 as "F" (do not put in the quotation marks). Clicking on Continue returns us to the Independent Samples t-Test box, where we click on OK to run the test, producing this output.
The first thing that you should note about this output is that the means show up as a series of asterisks (i.e. **********). This problem occurs infrequently, but you should know how to handle it. The reason for the asterisks is that there is not enough space for the numbers. You will need to create more space to see the numbers. You do this by moving the mouse pointer over this table and clicking the RIGHT button, which will will open a menu. You select the SPSS Pivot Table Object option, and then select open, which will give you this screen.
The window that you want to work on is labeled SPSS Pivot Table. You can either move or delete the other windows (Pivoting Trays and Formatting Toolbar). Delete them by clicking the X in the upper right hand corner. Move them by clicking and holding the left mouse button over the blue heading at the top of the window and dragging them to a free space on the screen. To make more room in the table for the means, you move the curser to the vertical line just to the left of the means. The cursor will turn into a small vertical line with arrows pointing in each direction. Hold the left mouse button down and move the cursor to the right. This will drag the line with it, making more room for the means. This screen shows the results of this reformatting. Click on the X in the upper right hand corner of the editing box and the output will now look like this screen.
This output is a bit complex. The first part of the output gives summary statistics for the two groups; the second part lists the inferential statistics. SPSS for Windows computes two t-values and their associated p-values--one based on the assumption of equal variances in the two groups and the other not requiring that assumption. Just to the left of the t-tests is a statistical test for the equality of the variances in the group. We consult the test for equality of variances to determine which t-test to use. In this case, the variances show a statistically significant difference (p=.021), so we use the t-test for unequal variances (the bottom one). The t is short of significance (p>.05), so we fail to reject the null hypothesis that there is a sex difference in salary levels.
Animations
We have prepared an animation that will walk you through this procedure. To run the animation, simply click on the title of the animation in the table below.
Note that we do not recommend that you try to run the animations if you have a slow connection, such as a dial-up connection. You will find that the animations take forever to load with a slow connection.