SPSS – Related Samples t-test 

The data example – Based on past research, an investigator believes that parents who use positive verbal statements (polite requests and suggestions) have children who are more socially accepted and more positive in interactions with peers.   Twenty first-grade children (who were rated by teachers and peers as aggressive) and their parents were selected for a study to determine whether a seminar on parenting techniques affects social competency in children.  The parents attended the seminar for one month. The children were tested for social competency before the course began and were retested six months after the completion of the course. The results of the social competency test are shown below. Higher scores indicate greater social competency.  Did the parenting seminar affect social competency in children?  Test with alpha of .05 and two tails.

 

Child	Pre	Post
1	3	34
2	26	25
3	32	38
4	38	36
5	29	29
6	34	41
4	24	26
8	35	42
9	30	36
10	36	44
11	31	28
12	27	32
13	25	25
14	28	30
15	32	41
16	27	37
17	37	39
18	29	33
19	31	40
20	27	28

 

STEP 1: Define variable name, label, and values

Open SPSS and choose Type in data. Start by naming the variables of interest. Click the Variable View sheet tab.  Type the variable name (8 characters max) in the Name column (e.g., Pretest). If needed, specify variable type, width, and number of decimals or simply accept the default settings. You have the option of typing a more descriptive variable name (255 characters max) in the Label column (e.g., Pre-Seminar Social Competency Score).  Now define the second variable (e.g., posttest).  It’s okay to accept the default settings for type, width, etc. Optional: it's a good idea to enter an identifier for each participant, so you may define a third variable (e.g., child).

 

STEP 2: Input the data into SPSS

     Click back into Data View.  Enter the data. Remember that the data from each participant is entered in a separate row in the data sheet.

 

STEP 3: Select the statistical procedures

Go to the Analyze menu and select Compare Means and then select Paired Samples T-Test.

 

STEP 4: Select the variables

Inside the subcommand box, select the variables whose means you want to compare. First, click on pretest and note that pretest immediately appears in the box labeled "Current Selections, Variable 1." Then click on posttest and note that it appears next to "Variable 2." Once you have the correct pair of variables, click on the right-arrow button. In the "paired Variables" box, the phrase posttest - pretest should appear. This indicates that in calculating difference scores, SPSS subtracts pretest from posttest (rather than the other way around). This becomes important when you interpret the results. The significance test test the hypothesis that in the population, the mean of these difference scores (posttest minus pretest) equal zero. Now click on OK to run the analysis.

 

STEP 5: Look up the t-statistic (p. 691) and make a conclusion regarding Ho.  You may also look at the two-tailed p-value which is provided in the output. Note that although the computed p-value for this problem is reported as ".000," this does not mean that there is a zero chance of making a type I error. SPSS rounds off p-values to three decimal places. So in reporting the results we would report p < .001.  We would make the decision to reject the null hypothesis. Then we study the means (34.2 for posttest and 30.45 for pretest) and conclude that the parenting seminar increased social competency scores for children whose parents attended the seminar and implemented the techniques.