12 - Correlational Strategy

Question 1

What the purpose of correlational?

Answer 1

Describe the nature of the relationship

Establish it exists

Question 2

What’s the diff between experimental study and correlational?

Answer 2

Experimental: measures one variable
Correlational: shows relationship between two variables

Question 3

What kind of chart shows correlational?

Answer 3

Scatter plot

Question 4

What does a correlation measure between two variables?

Answer 4

Direction of the relationship
Form of relationship (linear, Pearson)
Strength of the relationship (+1.00 or -1.00 for strong)

Question 5

Pearson correlation

Answer 5

Used to describe linear relationships when both variables are numerical scores from interval or ratio scales

Question 6

Monotonic relationship

Spearman correlation

Answer 6

Consistently one-directional relationship
Used to measure and describe monotonic relationships when both variables are ranks from an ordinal score or have been transformed to ranks

Question 7

What to do if one score is non-numerical?

Answer 7

Use the non-numerical variable to organize the scores into separate groups
If the non-numerical variable is 2 categories, calculate a point-biserial correlation
Code both categories as 0 and 1

Question 8

What to do if both categories are non-numerical?

Answer 8

Organize data in matrix
One variable rows
One variable columns
If each consist of two categories, code both as 0 and 1
Pearson correlation = phi-coefficient

Question 9

What is coefficient of determination?

Answer 9

Strength of relationship
Square numerical value of correlation
r squared
Measures how much of the variability in one variable is predictable from its relationship with other variable
Large relationship greater than r=0.50 or r2=0.25

Question 10

What is predictor variable and criterion variable?

Answer 10

GRE score, grad performance

One predicts the other (regression)

Question 11

How is correlational validity proven?

Answer 11

Test-retest from established tests

Question 12

When is correlational used?

Answer 12

Allows researchers to investigate variables is would be unethical to manipulate
Record what exists naturally
Low internal validity
Suggests relationships for further exploration using experimental method
High external validity

Question 13

Two limitations of correlational

Answer 13

Third variable problem
Directionality problem (which is cause? Effect?)

Question 14

Multiple regression

Answer 14

Multivariate relationships

Academic performance explained by several predictors like IQ, motivation