Correlation: Chapter 12 Flashcards
goal of correlational research
- establish that a relation/association exists between variables
- describe the nature of the relationship
manipulation and control of variables
no attempt to manipulate, control, or interfere with the variables
correlational data presentation
- each individual = two data points (one for each
variable) - data = presented in a table
- data points can be presented on a scatterplot
characteristics of the correlation
- form
- direction
- strength
form of the correlation
looking for pattern in data suggesting consistent and predictable relationship
* Linear relationship
* Non-Linear relationship
direction of the correlation
positive correlation (+)
- increases in 𝑥 are paired with increases in 𝑦
negative correlation (-)
- increases in 𝑥 are paired with decreases in 𝑦
strength of correlation
- degree of association between 2 variables
- expressed mathematically as the correlation
coefficient (r) - when the two variables are either ratio or
interval, we use Pearson r
strength of correlation (r)
- 𝑟 near 0 indicate weak relations
- 𝑟 close to -1 or 1 indicate that points lie close to
a straight line - 𝑟 equal to -1 or 1 indicate that points lie exactly
along a straight line
the regression line
- line is drawn through the points
- the closer the points are to the line, the greater the association between the variables
shared variance
- shared common ground between variables A + B
- r^2 = coefficient of determination = shared variance
correlational variables are ___
ordinal (not equal increments)
correlation matrix
refer to powerpoint on chapter 12, slide 25
correlation is not ___
causation
third variable problem (spurious correlation)
a third variable can cause A and B
directionality
correlating can suggest a direction
ex:
higher social media use causes depression
vs
depression causes higher social media use
correlations are useful for ___
predictions
regression analysis usage
- way of using associations between variables as a method of prediction
- predictor variable (IV)
- criterion variable (DV)
predictor variable
predicts y
criterion variable
y
reliability and validity
correlations can be used to determine reliability and validity
- test-retest reliability
- concurrent validity
evaluating theories
correlations can be used to evaluate theories
potential problems for pearson r
- correlation has to be linear
- when range of values measured for one of the variables is restricted; leads to misleading results.
correlation strengths
- can investigate unethical hypotheses
- helps identify where to look for causes
- high external validity
- record what exists naturally
correlation weaknesses
- cannot assess causality
- low internal validity