1
Experimental Design as a Research Strategy
" …
. A plan for assigning subjects to experimental conditions and
the statistical analysis associated with the plan."
(Kirk, 1995, p.1)
• What makes experimental research distinctive from other
research strategies?
• This course concerns:
• The plan or assigning subjects to experimental conditions.
• The statistical analysis for the plan.
• This course assumes:
• Equal number of subjects in all treatment conditions.
The Logic of Hypothesis Testing
• Hypothetical Example (twosample
t
test)
§
= 117,
= 125, and
n
1
=
n
2
= 31
§
Question: “Are the means significantly different?"
§
The null hypothesis and the alternative hypothesis;
H
0
:
μ
1
=
μ
2
H
1
:
μ
1
≠ μ
2
§
Results
t
= 1.25,
df
= 60,
p
= 0.108
1
X
2
X
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
2
Interpretation of
p
value
•
A small
p
value indicates that the obtained statistic is unusual, under
the assumption that the H
0
is true.
•
The smaller the
p
value, the more the data support rejecting the H
0
.
•
More formally,
p
value is the
probability of observing the size of
effect from the data or larger
, when H
0
is actually true.
•
In practice, you reject H
0
when the
p
value is smaller than a
predetermined
α
level.
(In the example)
• Predetermined
α
= 0.05
• Then, not reject the H
0
, because
p
is larger than 0.05.
• Conclude that the means are not
significantly different.
•
Another method of hypothesis testing is to compare the
obtained statistic and a corresponding critical value, without
computing the exact
p
value.
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '09
 THOMASBALDWIN
 Statistics, Null hypothesis, Type I and type II errors, critical value, SSTO

Click to edit the document details