Reading I NEED HELP ON MY HOMEWORK
4/4/2024
1
Research Methods
Getting to the truth:
The Scientific Method The scientific method is the process of testing our ideas about the world by:
setting up situations that test our ideas.
making careful, organized
observations.
analyzing whether the data fits with
our ideas.
If the data doesn’t fit our ideas, then we modify our ideas, and test again.
The Scientific Method
Acquiring knowledge through the formation of specific questions & systematic testing of those questions.
Steps in the Process
1. Understanding the theory
2. Develop hypotheses
3. Design study
4. Collect data and analyze findings
5. Report findings
4/4/2024
2
Theory: the big picture
Example of a theory: Social learning theory – Observing others engaging in prosocial behavior makes the observer more likely to engage in prosocial behavior.
Theory is an abstract system of
concepts and relationships that
help us understand a phenomenon or solve a problem.
Hypothesis •Hypothesis
• Testable prediction about relationship between variables
• Example
• Wearing a super hero costume makes people more prosocial
Methodology Basics
• Independent Variable: The variable that is observed or manipulated to see if it has an effect on another variable.
• Levels: number of conditions for a given IV
• Dependent Variable: The variable that is measured to see if it is being effected or influenced by the IV in any way.
4/4/2024
3
Costumes and Prosocial Behavior
• Hypothesis: Wearing a super hero costume makes people more prosocial
• IV:
• Costume or not
• DV:
• Measurement of prosocialness
How do we test hypotheses?
• Media Psychology Research:
• Non-Experimental Methods
• Surveys
• Experimental Methods
Survey research
• Surveys
• Self-reports of knowledge, feelings, experiences, attitudes, behavior, etc.
• Types
• Cross-sectional
• Longitudinal (trend, cohort, panel)
4/4/2024
4
population
Why take a sample?
• Sampling saves time. You can
find the ratio of colors in this jar
by making sure they are well
mixed (randomized) and then
taking a sample.
sample
Random sampling:
making sure that every
individual in a population
has an equal chance of
being in your sample.
“Random” means
that your selection of
participants is driven
only by chance, not
by any characteristic.
An observation that two
variables are related to
each other.
Especially useful when
you cannot manipulate
variables
Allow researchers to see
how two variables are
related.
The more years spent
smoking, the greater the
chance of lung cancer Correlations
Exposure to sexualized
advertisement associated
with dissatisfaction of
own body.
The greater the number
of Facebook friends, the
less time was spent
studying.
Correlation Coefficient
• A number that describes the strength of the relationship between two variables
• The + or – sign indicates whether this relationship is positive or negative
• Can vary from -1.0 to +1.0.
• -1.0 = perfect negative correlation
• 0.0 = no correlation
• +1.0 = perfect positive correlation
4/4/2024
5
Correlation Coefficient
Positive Correlation
• As the value of one variable increases, the value of the other variable increases
Comprehension of Miranda Rights
In te
ll ig
en ce
Positive Correlation
4/4/2024
6
Negative Correlation
• As the value of one variable decreases, the value of the other variable increases
No Correlation • Changes in one variable not associated with changes in other
variable
T em
p er
at u
re
Number of People with Hiccups
Correlation and Causation
• A correlation between X and Y does not mean that X causes Y
• All that is known is that X and Y are related in some way
4/4/2024
7
Ice Cream Does What?!?!
•Research has shown that when ice cream sales increase, so do the number of murders.
Ice Cream Sales and Crime
Amount of ice cream sold
C ri
m e
ra te
What is likely going on…
Crime
rate
Temperature
Ice cream
sold
4/4/2024
8
Correlational Design
• Advantages
• Study naturally occurring phenomena that cannot be manipulated
• Study phenomena that is unethical to create in lab
• Disadvantages
• CORRELATION DOES NOT EQUAL CAUSATION!!
• Third variable problem
So how do we find out about causation?
Experimentation:
manipulating one factor in
a situation to determine
its effect
IV: Costume or not
DV: Measurement of
prosocialness
Experimental Research
• Beyond just an observation between two variables
• When X increases, Y also increases
• A causal inference
• X is causing the change in Y
4/4/2024
9
Experimental Designs
•Experimental Design • Systematically manipulate one source of
influence while holding others constant
• Random assignment
•ONLY way to determine causality.
Just to clarify two similar- sounding terms…
First you sample, then you sort (assign).
Random assignment of participants to
control or experimental groups is how you control all
variables except the one you’re manipulating.
Random sampling is how you get a pool of
research participants that represents the
population you’re trying to
learn about.
Random Selection
•Rarely possible
•Any study where anyone, anywhere has the equal chance of being selected for that study??
•Random assignment is best solution • Evens out preexisting differences • Individual differences
• Reduces chance of confounds/third variables influencing results
4/4/2024
10
Eliminating Alternative Explanations •Use random assignment to assign
participants in experimental or control condition
• All persons have same chance of being in given condition
• Makes conditions equal
• Why can’t I let people choose what condition they want to be in?
Experiments
•Advantages
•Allow for causal conclusions
•Ability to tightly control environment
•Disadvantages
•Artificial situations
• Lack of generalizability
Evaluating all Research and Statements
• Be skeptical!!! Ask yourself: • Are they making causal statements w/ correlational
data? • Using unrepresentative sample or small sample? • Was random assignment used? • Are there enough study details? • Are they making generalizations that are just too
broad? • Have alternative explanations been eliminated?