Chapter 8
Hypothesis Testing With Two Samples
(Mean Difference and Difference of Means)
Outline
 Related Samples
a.
The Logic of the Test
b.
The Null Hypothesis
c.
Combining the Logic and the Null
d.
The Standard Error of the Mean Difference
e.
Applying the Test
f.
Interpreting the Results
g.
Some Additional Samples
 Independent Samples
h.
The Logic of the Test
i.
The Null Hypothesis
j.
Combining the Logic and the Null
k.
The Standard Error of the Difference of Means
l.
Applying the Test
m. Interpreting the Results
n.
Some Additional Examples
 Chapter Summary
I.
Related Samples
a.
To say that two samples are matched or related in some way is to say that the cases included in
the samples were not selected independently of one another.
i.
Before and after test situation a situation in which the participants are matched against
themselves
1.
Each person is tested twice and the focus is on any change in the test scores that
occurs between the first and second tests.
2.
Relation: Same People tested twice
ii.
Focusing on couples when the question is marriage calls for a matched or related sample
approach
1.
If we were just looking at random men and women it wouldn’t
b.
Matched or related samples are samples involving cases or subjects that share certain
characteristics in common
c.
The Logic of the Test
i.
What constitutes a difference?
ii.
To find the differences between to tests you subtract Test2 Test1 for each subject and
then add all of the differences and divide to get the mean difference pg. 801
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '10
 Cleveland
 Statistics, Standard Error, 814 g

Click to edit the document details