SPSS PROCEDURES for the independent groups t-test:

1.   Select the Analyze menu.

2.   Click on Compare Means and then Independent- 

     Samples T Test ....to open the Independent Samples

     T Test dialogue box.

3.    Select the test variable(s). [i.e. Inductive Reasoning] and

      then click on the        button to move the variables into

      the Test Variables(s): box     

4.    Select the grouping variables [i.e. gender] and click on

      the       to move the variable into the Grouping Variable: box 

5.    Click on the Define Groups ....command pushbutton to

      open the Define Groups sub-dialogue box.

6.    In the Group 1: box, type the lowest value for the variable

      [i.e.1 for 'males'], then tab. Enter the second value for the

      variables [i.e.2 for 'females'] in the Group 2: box.

7.    Click on Continue and then OK.

WORKING EXAMPLE:

t-Test for Independent Means or Independent Groups

The standard error of the difference (labelled "Std. Error Dif."), and the t obtained (labelled as "t") that results when the mean differences is divided by the standard error.

Levene's Test for Equality of Variances

F           Sig.             t              df     sig (2-tailed)   Mean            Std. error

                                                                                  difference    difference     Lower       Upper

  4.720       .030       - 4.875    944           .000            - 1.0468         -2147         - 1.4682      -.6254 

Equal variances assumed

Equal variances not assumed

- 4.853    911.407   .000            - 1.0468         -2147        - 1.4701      -.6234 

INDUCTIVE

Independent Samples Test

This second box contains the difference between the means (labelled "Mean Difference"); notice that 7.9512 – 8.9980 = – 1.0468.

The Independent Samples Test Output

• The SPSS output below displays the results of the t-test to test whether or not the difference between the two sample means is significantly different from zero.
  

• Remember the null hypothesis states that there is no real difference between the means (Ho: X1 = X2).
  

• Any observed difference just occurred by chance.
  

= This "t" value tells you how far away from 0, in terms

  of  the number of standard errors, the observed 

  difference between  the two sample means falls.

= The "t" value is obtained by dividing the Mean

  difference ( - 1.0468) by the Std. Error (- .2147) which

  is equal to - 4.875

Multiple Regression

T-test

Page 3 of 5

Page 3 of 5

A study was conducted in 2006 which assessed the inductive reasoning ability of 946 eighteen year old Malaysian adolescents. A 11 item test was administered. The researchers  were interested in  finding answer to the following question:

"Is there a significant difference in inductive reasoning between 18 year old males and females"?

THE SPSS STEPS to answer the Research Question.

= If the p-value as shown in the "sig (2 tailed) column is

  smaller than your chosen alpha level you do not reject

  the null hypothesis and argue that there is a real

  difference between the populations.

= In other words, we can conclude, that the observed

  difference between the samples is statistically

  significant.