*Correlations Flashcards
What is a correlation?
A mathematical technique in which a researcher investigates an association between 2 variables, called co-variables
Correlations do not imply causation.
What are co-variables?
The variables investigated within a correlation, for example, height and weight
Co-variables are often referred to as independent and dependent variables.
What does correlation measure?
The strength and direction of an association between 2 or more co-variables
Correlation does not show a cause and effect relationship.
How are correlations plotted?
Plotted on a scattergraph with one co-variable on the x-axis and another on the y-axis
Each dot on the graph represents the x and y position of each co-variable.
What is a positive correlation?
As one variable increases, the other increases too
Example: Frequent use of caffeine is correlated with high anxiety.
Provide an example of a positive correlation.
Frequent use of caffeine is correlated with high anxiety
This can be assessed by asking how much caffeine people drink and self-reporting anxiety levels.
What is a negative correlation?
As one variable increases, the other decreases
Example: Frequent use of caffeine is correlated with lack of sleep.
Provide an example of a negative correlation.
Frequent use of caffeine is correlated with lack of sleep
This can be assessed by recording sleep duration alongside caffeine intake.
What is zero correlation?
No relationship between the 2 variables
Example: Amount of caffeine drank and the number of dogs seen each week.
What is the difference between correlations and experiments?
In an experiment, the researcher manipulates the IV to measure its effect on DV; correlations do not involve manipulation
Correlations cannot establish cause and effect.
What are curvilinear relationships?
More complex than positive or negative correlation; performance increases to an optimal point of arousal and then declines
This is illustrated by the Yerkes-Dodson law of arousal.
What are some strengths of correlations?
Useful preliminary tool, quantifiable measure of relationships, suggests new research ideas, quick and economical
No need for controlled equipment or manipulation of variables.
What are some limitations of correlations?
Lack of control means we can’t determine why variables are related, can’t demonstrate cause and effect, potential for extraneous variables
Correlations can be misused or misinterpreted in media.
