1. Chapter 4 Studying Behavior
Variables
Can have levels
Types
1. Situational
Characteristic of the environment
2. Response
Reaction time, performance on a task
3. Participant or subject
Gender, personality trait
4. Mediating
Personal responsibility

2. Operational definition
A definition of the variable in terms of the operations used to measure it [the variable]
Defines a construct by specifying how it [the construct] is measured or manipulated
Converts an abstract concept into concrete, situation specific terms
For example
In animal research  Hunger: deprivation for at least 12 hours
In human research 
How hungry are you at this moment?
Not at all
Slightly
Moderately
very

3. Operational definition
Necessary for empirical study
Can be easily assigned or abstract
Helps to communicate ideas in the scientific community
However, researchers from different labs can define similar things differently

4. Variables Usually thought to have a cause and effect connection
Independent variable
The “cause”
Manipulated in an experiment
Must have 2 or more levels
Can be quantitative (i.e. different doses of a drug) or qualitative (i.e. changing the sequence of words in a memory test).
It is usually on the horizontal axis (x axis) on a graph
Dependent variable
The “effect”
Measured in an experiment
Can have one or more levels
It is usually on the vertical axis (y axis) on a graph

5. For example
Homer notices that his shower is covered in a strange green slime. His friend Barney tells him that coconut juice will get rid of the green slime. Homer decides to check this this out by spraying half of the shower with coconut juice. He sprays the other half of the shower with water. After 3 days of "treatment" there is no change in the appearance of the green slime on either side of the shower.
What was the initial observation?
Identify the
Control Group
Independent Variable
Dependent Variable
What should Homer's conclusion be?

6. Relationships b/w variables
Comparing values along a numeric scale
Positive linear relationship
Increases in one variable (on x axis) are accompanied by increases in another variable (y axis)
For example
Are fast talkers more persuasive?
Plot words spoken per minute (x axis) against attitude change (y axis)
Negative linear relationship
Increases in one variable are accompanied by decreases in the other variable
Does the number of people in a group predict how efficient the group will be?
One study found that as the size of the group increased, the amount of noise decreased.

7. Relationships b/w variables
Curvilinear relationship
Increases in one variable are accompanied by decreases and increases in the other variable
Referred to as U shaped curves or inverted U shaped curves
For example
In dose response studies, in the case of a U shaped curve,
low doses can cause high responses
Intermediate doses can have low effectiveness
High doses can cause high responses
No relationship
Does the length of the tail of a bird predict how many matings it will engage in?

8. Nonexperimental vs. experimental methods
Making observations of the variables of interest
Asking others to describe their behavior
Examining public records
Allows for observation of covariation between variables
Correlational method

9. Nonexperimental vs. experimental methods
Problems with correlational method
Direction of cause and effect
The 3rd variable problem

10. Nonexperimental vs. experimental methods
Involves direct manipulation and control of variables
The researcher manipulates the 1st variable and observes the response
Reduces ambiguity in the interpretation of results
The direction of cause and effect is clear
Attempts to eliminate the influence of all potential confounding variables
Control of extraneous variables

11. Nonexperimental vs. experimental methods
Experimental control
Control of extraneous variables
Variables held constant cannot be a confounding variable
Accomplished by treating participants/subjects in all groups in the experiment identically
Randomization
Ensures that the extraneous variable is equally likely to affect all participants/subjects
Eliminates influences of individual characteristics
Ensures that the composition of participants/subjects in each group is identical

12. Causality Inferences about causality require 3 elements-
Is the cause “necessary and sufficient” for the effect to occur?

13. Choosing methods Field experiment
Done in the “field”, not the laboratory
The independent variable (i.v.) is manipulated in a natural setting
Advantage: -
Disadvantages:

14. Evaluating Research Validity
The accurate representation of information
Different types (each gives a different perspective on a research investigation)
Construct validity
The adequacy of the operational definition of variables
The measure has construct validity if it measures what it is supposed to
Face validity
Criterion oriented validity
Internal
The ability to draw conclusions about causal relationships from the data
Easier to prove when using the experimental method

15. Evaluating Research No method is superior to another Internal External
Threats
Biased assignment of subjects
Experimental confounds (i.e. performing systematic differences)
Differential attrition
Pretest sensitization
External
The extent to which the results can be generalized to other populations and settings
Can these results be replicated? With different participants?
No method is superior to another