Scribd
Upload
6 views

Lesson 4

The document discusses using a t-test to compare the means of two independent groups on a dependent variable. It provides the objectives, requirements, assumptions, and steps to conduct an independent t-test using SPSS software. An example compares the number of words correctly recalled between male and female groups. The t-test output is presented and interpreted, with results showing no significant difference in group means.

Uploaded by

camilleescote562
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
6 views

Lesson 4

The document discusses using a t-test to compare the means of two independent groups on a dependent variable. It provides the objectives, requirements, assumptions, and steps to conduct an independent t-test using SPSS software. An example compares the number of words correctly recalled between male and female groups. The t-test output is presented and interpreted, with results showing no significant difference in group means.

Uploaded by

camilleescote562
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 13

Lesson 4: T-Test Independent Groups

Objectives At the end of this lesson, you shall be able to:

• decide when to use T-Test


• compare variables obtained from two independent
samples
• recognize requirements and assumptions for the test
• use SPSS software for a given sample
• produce T-Test output
• translate data output into general statements
Putting your mind into action / Putting your ideas into work

Aim
The independent t-test is used for testing the difference between
the means of two independent groups. It is particularly useful
when the research question requires the comparison of variables
obtained from two independent samples. For example:
• “Do males and females differ in performance on a standardized
achievement test?”
• “What is the effect of drug vs. no drug on rats’ maze-learning
behavior?”
• “Does the recidivism rate of juvenile offenders who are provided
with father figures differ from those without father figures?”
Checklist of Requirements

In any one analysis, there must be:

• Only one independent (grouping) variable (IV) (e.g., subject’s gender)


• Only two levels for that IV (e.g., male and female)
• Only one dependent variable (DV)
Assumptions
• The sampling distribution of differences between means is normally distributed.

• Homogeneity of variance.
• Level of Measurement
• Random Sampling
• Independence of Observations
Example
Males Females

s1 16 s11 24
s2 14 s12 23

s3 18 s13 26

s4 25 s14 17

s5 17 s15 18

s6 14 s16 20

s7 19 s17 23

s8 21 s18 26

s9 16 s19 24

s10 17 s20 20
Data Entry Format

The data set has been saved under the name: EX4.SAV.

Variables Column Code


Gender 1 1 = male, 2 = female
Words 2 2 Number of words
correctly recalled
Windows Method

1.From the menu bar, click Analyze , then Compare Means , and then Independent-
Samples T-test.

2. Because GENDER is the grouping (independent) variable, transfer it to the Grouping


Variable field by clicking (highlighting) the variable and then clicking. As WORDS
is the test (dependent) variable, transfer it to the Test Variable(s) field by clicking
(highlighting) the variable and then clicking.

3.Click to define the range for the grouping variable of GENDER (coded 1 =
male, 2 = female). When the following Define Groups window opens, type 1 in the
Group 1 field and 2 in the Group 2 field, and then click.
4. When the following Independent-Samples T Test window opens, run the T-Test
analysis by clicking .
SPSS Output
Results and Interpretation

Levene’s Test for Equality of Variances tests the hypothesis that


the two population variances are equal. In this example, the Levene
statistic is F = 0.087, and the corresponding level of significance is large
(i.e., p > .05). Thus, the assumption of homogeneity of variance has not
been violated, and the Equal variances assumed t-test statistic can be
used for evaluating the null hypothesis of equality of means. If the
significance level of the Levene statistic is small (i.e., p < .05), the
assumption that the population variances are equal is rejected and the
Equal variances not assumed t-test statistic should be used.
EFFECT SIZE
Eta Squared

You might also like