|
I. Introduction
A.
Conceptual perspective
1.
Comparing the means of the different groups
2.
Mean differences can be due to IV, confound, or error
3.
Comparing the results (means) we obtain with what we might expect by
chance
B. The role of probability
1.
Chance and error
2.
Could these results have occurred by chance?
e.g.,
consider two means 12.0 and 13.0
All
things being equal, we are more convinced when we see larger differences
between means. Why?
II.
Hypothesis testing
A.
Null hypothesis/Experimental hypothesis
B.
Fail to reject vs. reject
C.
Making decisions and making mistakes
Possible
outcomes:
|
|
|
Decision
|
|
|
|
Reject Null
|
Fail to reject Null
|
|
What is true in
the population?
|
Null is false
|
CORRECT
(Power)
|
Type II error
(β)
|
|
Null is true
|
Type I error
(α)
|
CORRECT
|
1.
Type I error
2.
Type II error
Which error is worse?
3.
Power
Power
is increased by:
III.
Inferential Statistics
A. What do we mean by
inference?
B.
t-test
t
= association/lack of association
1.
calculate means
2.
calculate variance
3.
compute t
4.
find critical t, given specified alpha
5.
compare obtained t with critical t; make decision
degrees
of freedom
C.
Chi-square (handout)
|
