Transcript 3220Lecture8Chapter7

Marketing Research
4/7/2016
1

Allow demonstration of causality
◦ A causes B

Relatively small sample sizes needed
◦ Minimum of 20 per experimental “cell”
Marketing Research
4/7/2016
2

CAUSE
◦ Independent variable

OUTCOME
◦ Dependent variable
CAUSE
OUTCOME
Marketing Research
4/7/2016
3
1.
Temporal ordering of variables
2.
Evidence of association
(“concomitant covariation”)
3.
Control of other causal factors
Marketing Research
4/7/2016
4
Setting
•Laboratory
•Controlled setting.
•Field
•Natural environment, such as a store or mall
5
Validity
Internal:
The extent to which competing explanations for
the findings observed can be ruled out.
External:
The extent to which the findings will apply to
outside persons, settings, and times.
6

Manipulate variable of interest
◦ Independent variable: IV
◦ (Variable we can control)

Hold all else constant
◦ Extraneous variables

Measure outcome
◦ Dependent variable: DV
◦ (Variable we cannot directly control)
Marketing Research
4/7/2016
7
Researchers at Madigan Army Medical Center examined effectiveness of
duct tape on warts.
The 51 patients between 3 and 22 were randomly assigned to receive either
cryotherapy or duct tape. Patients in the cryotherapy group received a
standard 10 second application of liquid nitrogen, repeated every two to
three weeks. In the other group, a small piece of duct tape was placed on
the patients' warts and patients were told to keep the tape on for six days.
At the end of six days, they removed the tape, soaked the area in water,
and used an emery board or pumice stone to rub the dead skin off.
Warts were successfully removed in 60 percent (15 of 25) of the patients in
the cryotherapy group versus 85 percent (22 of 26) of the patients in the
duct tape group. The duct tape group reported fewer side effects than
cryotherapy group who reported pain and burning at the site.
Overall, the researchers found duct tape to be more effective, less painful,
and less expensive than freezing.
Marketing Research
4/7/2016
8

Assignment to condition
◦ Randomly assign subjects to condition OR
◦ Match subjects on variable of interest

Manipulation
◦ Experimental group gets it
◦ Control group does not get it

Measurement of DV
◦ Pretest
◦ Posttest
Marketing Research
4/7/2016
9


Pretest posttest control group design:
◦ Experimental Group
R O 1 X O2
◦ Control Group
R O3
O4
Posttest only control group design:
◦ Experimental Group
R
X O1
◦ Control Group
R
O2
Marketing Research
4/7/2016
10
Design
that investigates the effect of two
or more independent variables on a
dependent variable
Allows
testing of interactions and
contingent conditions
Marketing Research
4/7/2016
11
Ad A
Ad B
Men
65
Main Effects
> of Gender
Women
65
70
60
Main Effects of Ad
100
90
Interaction Between Gender and
Advertising Copy
80
70
60
50
40
30
20
10
Ad A
Ad B

Experimental research is the best way to test
causation.

Experimental research is inherently
reductionistic.

Complex designs allow the comparison of
several factors simultaneously, including
interactions.
Marketing Research
4/7/2016
14
Marketing Research
4/7/2016
15