Midterm #2 & #3 - Correlational Designs Flashcards
1
Q
correlational study
A
- a research approach that focuses on how variables relate to one another
2
Q
purpose
A
- identify relationships between variables
- measure strength and direction of relationship
3
Q
directionality
A
- determines if relationship is positive or negative
4
Q
strength of association
A
- uses statistical method to measure strength of variable relationships
- indicated by correlation coefficient
5
Q
no causal inference
A
- can’t prove that changes in one variable causes changes in another
6
Q
advantages
A
- more natural setting and context
- carried out when ethics or manipulation not possible
- explore relationships or differences in more detail before trying to manipulate or identify causal variables
7
Q
limitations
A
- doesn’t restrict or manipulate confounding variables
- no manipulation, too many extraneous variables may exist to infer causality
8
Q
spurious correlation
A
- look related but aren’t
- actually a 3rd variable
9
Q
positive relationships
A
- increase in the values of one variable are associated with increases in the 2nd variable
- elevator
10
Q
negative relationships
A
- increases in the values of the one variable associated with decreases in the 2nd variable
- see-saw
11
Q
linear relationships
A
- more specific example of a general class of functions known as monotonic functions
- don’t change the direction of their slope
12
Q
curvilinear relationships
A
- increases in the value of one variable associated with both increases and decreases of the 2nd variable
- nonmonotonic
13
Q
correlation matrix
A
- summarizes the correlations between every possible pair of variables in a study
14
Q
content validity
A
- measure reflects all the relevant domains of the concept being assessed
15
Q
face validity
A
- measure is acceptable and understood by the target population
16
Q
construct validity
A
- measure corresponds to theoretical concepts
17
Q
concurrent (criterion) validity
A
- measure correlates well with similar measures or behaviours
18
Q
predictive validity
A
- measure predicts future events
19
Q
test-retest reliability
A
- compares reliability of test over two time points
20
Q
internal reliability
A
- consistency of items on a total/subscale
21
Q
split half reliability
A
- separate data into 2 halves and check the correlation between halves
22
Q
Cronbach’s Alpha
A
- correlation coefficient
- equivalent of all possible split halves
23
Q
exploratory factor analysis
A
- understand the structure of a set of variables
- develop/refine a questionnaire measure to assess an underlying construct
- reduce a dataset to a more manageable size for analysis