How to Create T-Test Graphs
Social scientists use SPSS (Statistical Package for the Social Sciences) to conduct t-tests. T-tests compare the means of responses, either from the same sample at two different points in time, or from two different samples of people. The analysis will provide the t-value (test statistic) and the significance (the probability the difference between the groups is due to chance rather than the predictor variable). The results of the t-test can be used to create a graph in SPSS. The graph is a visual representation of the results.
Things You'll Need
Load SPSS. Click on "File" at top of screen and select "Open" from the drop-down box. Double-click on the file you want to use. Click "Open." Click on "Data View" at the bottom of the SPSS screen. This will show your data.
Click on "Statistics" in the tool bar at the top of the page. Select "Compare Means" in the drop-down box. Click on "Independent Samples T-Test."
Look at the list of variables on the left of the box. Highlight your dependent variable -- for example, "Scores" -- while holding down the "Shift" button and move it to the "Test Variable" box.
Highlight your predictor variable -- for example, "Sex" -- while holding down the "Shift" button and move it to the "Grouping Variable" box. Click "OK."
Review the results that appear in the output window. The important information is the t-value (for example, 2.48) and the significance (for example, .02). A significance of .02 means there are two possibilities out of 100 that the results are due to chance.
Go to the SPSS screen, click on "Data View" and then click on "Graphs" at the top. When the dialog box appears, click on "Bar." When the next dialog box appears, select "Simple." Click on "Define," which provides another dialog box.
From the list of your variables on the left, select the variable you wish to have on the category axis (the X axis), your predictor variable (for example, "Sex"). Click on the arrow button pointing right to send that variable into the "Category Axis" box.
Indicate the type of dependent variable (number of cases, percentage of cases, etc.) or in this case click on "Other Summary Function." From the list of variables on the left, select the dependent variable -- for example, "Scores" -- and click on the arrow button pointing right to put it in the "Variable" box. Click "OK."
Review the output that will display your graph with "Sex" in the X axis and the bars showing the mean "Scores." Double-click on the graph to open the Chart Editor to change any properties of the graph.
Tips & Warnings
- Save data frequently.
- Save output.