Chapter 4: Fundamental Research Issues
Variables
General class or category within which specific instances vary
Characteristics of people, situations, and behavior
Must have 2 or more levels
Dress
Attractiveness
Operational Definition
Precise definition of your variables
Fast cars get more tickets
The effects of crowding on aggression in rats
Relationships Between Variables
How variables go together
Allows for prediction
TV violence and aggression
Range from .00 to 1.00
Can be positive or negative
Positive Relationship
aka direct relationship
As the value of one variable increases, so does the value of the other
Consumption of ice cream and violence in New York City
Negative Relationship
aka inverse relationship
As the value of one variable increases, the value of the other decreases
Smoking and grades in college
Curvilinear Relationship
As the value of one variable increases, the value of the other increases and decreases
Light brightness and work productivity
No Relationship
Increases or decreases in the value of one variable are not associated with the other
Age and driving ability
Methods of Research
Correlational: Variables are measured
Experimental: Variables are manipulated
Correlational Method
Non-manipulative
Two Problems:
1. Cause and effect2. 3rd variable problem
Cause and Effect
* Which variable caused the other?
3rd Variable Problem
* Major Flaw!!
*Some other variable is responsible for the relationship
Experimental Method
Cause and effect determined
Experimental control
* extraneous variables kept constant
Randomization
Independent Variable (IV)
Manipulated by the researcher
What the researcher “does” to the participant
The presumed “cause”
Dependent Variable (DV)
The variable of interest
Depends on the value of the IV
What the participant “does back” to the researcher
The presumed “effect”
Graphing
Causality
A change in one variable produces a change in the other
Necessary and Sufficient Causes
* Frustration sufficient = aggression
* Necessary to be 21 to legally drink
Either is acceptable for psychologists
Which Method to Choose?
Weigh advantages and disadvantages
* Lab experiments very artificial* Correlation Causation
Field Experiments
IV manipulated in a natural setting
Langer, Janis, & Wolfer (1975)
* Studied patients ability to cope with pain
Ethical Considerations?
Can choose our method for us
Effectiveness of spanking on behavior modification in children
* Random assignment?!
Participant Variables
Cannot be manipulated
Not able to use “true” random assignment
Age, race, etc.
Causation or Prediction?
Depends which one you are interested
What is the goal of the SAT?
* Criterion & predictor variables
What is the goal of studying aggression?
Validity: Evaluating Research
Validity: what is it?
1. Construct Validity
2. Internal Validity
3. External Validity
Construct Validity
Does the measure actually assess what it was intended to measure
Applies to measures that are not directly observable
Intelligence
Self-esteem
“Goodness” of the operational definition
Internal Validity
Does the IV “cause” the DV?
External Validity
Examines issues of generalizability