8/31/2015
Moderate (Positive) Correlation
Negative Correlation
Slide 2
What Kind of Correlation?
Our ADHD Example :
Is Hyperactivity Correlated in Twins?
• Research has shown a correlation between low
levels of brain serotonin and increased
aggressiveness in children
• In those with Alzheimer’s disease, the lower the
levels of ACh in brain, the lower their scores on
memory tests.
• Among gorillas, the larger the alpha male, the
less likely he is to be challenged by other males.
• Male fraternal twins show almost no
correlation (+.05) in their level of activity
• But male identical twins show a strong
correlation (+.71) in their level of activity
• Supports the hypothesis that genetics play a
role in ADHD, but does not prove a causeeffect relationship.
Correlations DO NOT imply causal
relationships
Research Methods in Psychology
Violent crime
• Descriptive Methods
A classic
example of
the “third
variable
problem”
•
•
•
•
Intensive individual case study
Naturalistic observation
Surveys/questionnaires/interviews
Correlational studies
• The Experimental Method
• for determining cause-effect relationships
Ice cream sales
1
8/31/2015
Why is an experiment
different?
• Tests hypothesis by comparing the behavior of
2 or more groups of participants under very
controlled conditions.
• Groups are treated as similarly as possible
EXCEPT for the critical variable (the
independent variable) that the researcher is
interested in.
• The researcher intentionally manipulates or
varies the independent variable to study its
impact on behavior, while keeping everything
else constant.
Hypothesis
• A testable statement or prediction about the
relationship between 2 or more variables
• Examples:
• Consumption of alcohol will impair short-term
memory.
• Relaxation training will reduce test anxiety and
improve test performance.
• Watching a violent video will increase violent
behavior.
Random Assignment
• Another
example in Stepby-step on p 27
Definitions:
• Experimental group – the participants
exposed to the independent variable that the
researcher is really interested in
• Control group – the participants NOT
exposed to the independent variable of
interest but rather to some substitute control
condition.
• To make the 2 groups as equal as possible initially, most often
participants will be randomly assigned to 1 group or the other.
This assures that there are no systematic differences between
the groups.
Definitions:
• Independent variable- what the investigator
manipulates or varies; the thing that is different
in the experimental group versus the control
group.
• Dependent variable - the behavior that is
observed, measured, tested; the actual data
collected from both groups.
• The researcher must define both the
independent & dependent variables as they will
be used in his/her study: These are
“operational definitions”
2
8/31/2015
Eliminating Bias
Operational Definition
• A definition that describes the actions or operations that will be
made to manipulate, measure, or control a variable in an
experiment
• In any experiment the researcher has to define the independent
and dependent variables.
Research on Multi-tasking
• Humans are NOT good at it
• Not truly able to pay attention to 2 complex tasks at
once – must switch attention back and forth,
missing info
• We’ve all heard about the dangers of texting while
driving, but it need not be a MANUAL task to disrupt
attention and behavior.
• We have had 2 examples studies that involve
“single-blind” procedures (collage evaluators and
interview transcribers)
• Some experiments do even more to avoid bias
• Double-blind experiments – neither the participant
nor experimenter knows (until after the data are
collected) which group/condition the individual is in
• Fascinating and important research by Dr. David
Strayer
• Studied the effect of hands-free cell phone use on
driving behaviors
• Used high quality driving simulator with Ford Crown
Vic dashboard and controls
• Hypothesis 1: talking on cell phone will impair
driving more than talking to passenger during 24
mile “drive” to specific location
• This experiment used 3 groups
• http://www.psych.utah.edu/psych4130/cellphone.w
mv
Successful Navigation to
Rest Stop
Lane Keeping Errors
1.2
100
% Correct Exit
RMS Error
1
0.8
0.6
0.4
60
40
20
0.2
0
80
Cell Phone
Passenger
Single-Task
0
Cell Phone
Passenger
Single-Task
3
8/31/2015
How Significant is the Interference?
Reaction Time When Braking
 Hands-free Cell-phone vs. drunk-driver
1050
 Hypothesis 2 – talking on cell will impair driving
as much or more than driving intoxicated
Reaction Time
1000
950
900
850
800
750
700
Intoxicated Driving
Cell-Phone Driving
Rear-end Collisions
Rear-end Collisions
4.0
3.5
3.0
2.5
2.0
1.5
1.0
0.5
0.0
Intoxicated Driving
Cell-Phone Driving
The Gazing Study
• Equal numbers of males and females randomly
assigned to 2 groups, then males in each group
randomly paired with females in that group.
• Group 1 – Eye gaze condition
• Group 2 – Hand gaze condition
• Group 1 reported feeling more emotionally attracted
to their partners
• Use of deception in research
“Experiments” That Are Not Quite
True Experiments:
Quasiexperiments
• Sometimes we need to use pre-existing groups
in research (e.g. males vs females, alcoholics
vs non-alcoholics). Since we can’t randomly
assign participants to groups, there may be
other differences between the groups that
impair our ability to draw conclusions.
• http://www.psychologytoday.com/blog/homo-consumericus/201105/sexdifferences-in-accepting-solicitations-casual-sex
Be sure to read about other ethical guidelines for Psych research.
4