Chapter 9: Analysing relationships between variables using SPSS

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file screening.sav and open it.
2. Tell SPSS to display meaningful labels for the variable names.
1. Select the window showing the screening dataset.
2. Click on Variable View (at the bottom of the window).
3. Click the Label box/cell next to the parent variable.
4. In the Label box type Parent questionnaire score.
5. Click the Label box/cell next to the mdi variable.
6. In Label box type Mental Development Index.
3. Tell SPSS to make a scatterplot.
1. From the Graphics menu choose Chart Builder....
2. If a window appears asking you to set measurement level, click OK.
3. Click the Gallery button (in the lower part of the window).
4. Click Scatter/Dot.
5. Double click the left picture (the Simple Scatter plot).
6. Drag parent to the X-Axis? place holder in the graphic preview (the right windowpane).
7. Drag mdi to the Y-Axis? place holder in the graphic preview.
8. Click the Titles/Footnotes button (it is near the middle of the window but you may need to click the right facing triangle first).
9. Check the Title 1 checkbox button.
10. In the Element Properties window in the Content: box type Scatter plot of MDI by parent questionnaire score.
11. Click Apply.
12. In the Element Properties window in the Edit Properties of: box select Y-Axis1 (Point1).
13. In the Scale Range area uncheck the Automatic checkbox next to Minimum.
14. In the Custom box next to Minimum type 40.
15. Click Apply.
16. Click OK.
4. Tell SPSS to calculate the correlation between parent and child scores.
1. From the Analyze menu choose Correlate > Bivariate....
2. Drag mdi and parent to the Variables: box.
3. Click OK.
5. Annotate the graphic to include numeric details.
1. Double click the scatterplot in the output.
2. From the Options menu choose Text Box.
3. In the text box type r = 0.68 (N = 64, P < .001).
4. Drag the text box to a corner of the plot that does not have data.
5. Click OK.

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file babyanth.sav and open it.
2. Tell SPSS to make a scatter plot matrix.
1. From the Graphics menu choose Legacy Dialogs > Scatter/Dot....
2. Click the Matrix Scatter button.
3. Click the Define button.
4. Drag Weight, Head, Arm and Length into the Matrix Variables: box.
5. Click OK.
6. Double click the graphic.
7. In the Chart Editor window double click the body of the graphic.
8. Click the Gallery button (in the lower part of the window).
9. In the Properties window click the Chart Size button.
10. In the Height box set type 500.
11. Click Apply.

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file babyanth.sav and open it.
2. Tell SPSS to calculate a correlation matrix.
1. From the Analyze menu choose Correlate > Bivariate....
2. Drag Weight, Head, Arm and Length into the Variables: box.
3. Click OK.

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file tbmeals.sav and open it.
2. Tell SPSS to compute the log transform of TB rate.
1. From the Transform menu choose Compute Variable....
2. In the Target Variable: box type loggedTB.
3. In the Function group: box select Arithmetic.
4. In the Functions and Special Variables: box double click LG10.
5. Double click on TB.
6. Click OK.
3. Tell SPSS to display meaningful labels for the logged TB variable.
1. Select the window showing the screening dataset.
2. Click on Variable View (at the bottom of the window).
3. Click the Label box/cell next to the loggedTB variable.
4. In the Label box type Type Log10(TB rate / 1000000 pop).
4. Tell SPSS to calculate the correlation betweeen TB rates and the percentage of children who receive free meals.
1. From the Analyze menu choose Correlate > Bivariate....
2. Drag tb, loggedTB and meals to the Variables: box.
3. Click OK.
5. Tell SPSS to make scatterplots.
1. From the Graphics menu choose Chart Builder....
2. If a window appears asking you to set measurement level, click OK.
3. Click the Gallery button (in the lower part of the window).
4. Click Scatter/Dot.
5. Double click the left picture (the Simple Scatter plot).
6. Drag meals to the X-Axis? place holder in the graphic preview (the right windowpane).
7. Drag tb to the Y-Axis? place holder in the graphic preview.
8. Click the Titles/Footnotes button (it is near the middle of the window but you may need to click the right facing triangle first).
9. Check the Title 1 checkbox button.
10. In the Element Properties window in the Content: box type (a) Raw data: r = .45, P < .01.
11. Click Apply.
12. Click OK.
13. From the Graphics menu choose Chart Builder....
14. If a window appears asking you to set measurement level, click OK.
15. Click the Gallery button (in the lower part of the window).
16. Click Scatter/Dot.
17. Double click the left picture (the Simple Scatter plot).
18. Drag meals to the X-Axis? place holder in the graphic preview (the right windowpane).
19. Drag tb to the Y-Axis? place holder in the graphic preview.
20. Click the Titles/Footnotes button.
21. Check the Title 1 checkbox button.
22. In the Element Properties window in the Content: box type (b) Log-transformed data: r = .46, P < .01.
23. Click Apply.
24. In the Edit Properties of: section, select Y-Axis1 (Point1).
25. In the Scale Range section uncheck the Automatic checkbox next to Minimum.
26. In the Custom box next to Minimum type 3.
27. In the Scale Range section uncheck the Automatic checkbox next to Maximum.
28. In the Custom box next to Maximum type 40.
29. In the Scale Type section set the Type: dropdown to be Logarithmic.
30. Click Apply.
31. Click OK.

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file screening.sav and open it.
2. Tell SPSS to calculate the correaltion betweeen parent and child scores.
1. From the Analyze menu choose Correlate > Bivariate....
2. Drag mdi and parent to the Variables: box.
3. In the Correlation Coefficients section uncheck the Pearson checkbox.
4. Check the Kendall's tau-b checkbox.
5. Click OK.

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file pefr.sav and open it.
2. Tell SPSS to make a scatterplot.
1. From the Graphics menu choose Chart Builder....
2. If a window appears asking you to set measurement level, click OK.
3. Click the Gallery button (in the lower part of the window).
4. Click Scatter/Dot.
5. Double click the left picture (the Simple Scatter plot).
6. Drag age to the X-Axis? place holder in the graphic preview (the right windowpane).
7. Drag perf to the Y-Axis? place holder in the graphic preview.
8. Click OK.
9. Double click the graphic.
10. From the Elements menu choose Fit Line at Total.
11. In the Properties window click Fit Line (at the top of the window).
12. In the Fit Method section click the Linear radio button.
13. Uncheck the Attach label to line checkbox.
14. Click Apply.
15. Click on the R squared Linear = 0.178 label and push delete on your keyboard.

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file pefr.sav and open it.
2. Tell SPSS to do a simple regression predicting PERF with age.
1. From the Analyze menu choose Regression > Linear....
2. If a window appears asking you to set measurement level, click OK.
3. Drag perf to the Dependent: box.
4. Drag age to the Independent(s): box.
5. Click Statistics....
6. In the Regression Coefficients section check the Confidence intervals checkbox.
7. Uncheck the Model fit checkbox.
8. Check the Descriptives checkbox.
9. Click Continue.
10. Click OK.

The regression model and the basic scatterplot with regression are shown above. This version just adds the confidence bounds and the CLs on the prediction.

1. Open the file.
1. From the File menu choose Open > Data....
2. Find the file pefr.sav and open it.
2. Tell SPSS to make a scatterplot.
1. From the Graphics menu choose Chart Builder....
2. If a window appears asking you to set measurement level, click OK.
3. Click the Gallery button (in the lower part of the window).
4. Click Scatter/Dot.
5. Double click the left picture (the Simple Scatter plot).
6. Drag age to the X-Axis? place holder in the graphic preview (the right windowpane).
7. Drag perf to the Y-Axis? place holder in the graphic preview.
8. Click OK.
9. Double click the graphic.
10. From the Elements menu choose Fit Line at Total.
11. In the Properties window click Fit Line (at the top of the window).
12. In the Fit Method section click the Linear radio button.
13. In the Confidence Intervals section click the Individual radio button.
14. Click Apply.
15. From the Elements menu choose Fit Line at Total.
16. Use the information on the regression line to write the regression equation. Type PEFR = 89.4 + 21.8 * Age.
17. Double click the equation attached to the regression line..
18. In the Properties window click the Reference line button.
19. Uncheck the Attach label to line checkbox.
20. Click Apply.
21. Click on the R-squared Linear = 0.178 label and push delete on your keyboard.