Chapter 7: Correlational Research

Question 1

Correlational Research

Answer 1

Used to describe the relationship between two or more naturally occurring (not experimentally manipulated) variables (e.g. is age related to political conservatism?).

Question 2

Correlation Coefficient

Answer 2

A statistic that indicates the degree to which two variables are related to one another in a linear fashion.

Question 3

Correlation: Measures of Effect Size

Answer 3

Small: r = .10
Medium: r = .30
Large: r = .50

Question 4

Covariability

Answer 4

The extent to which two variables vary together; r is the ratio of covariability to total variability.

Question 5

Coefficient of Determination (r squared)

Answer 5

The proportion of variance in X explained by its relationship to Y (the proportion of shared variance); r squared is a ratio scale of measurement, whereas r is not.

Question 6

The statistical significance of r is affected by which three things?

Answer 6

1. Sample Size
2. Magnitude of the Correlation (Effect Size)
3. Alpha or Significance Level

Question 7

Restricted Range

Answer 7

Data in which participants’ scores are confined to a narrow range of the possible sores; artificially lowers correlations.

Question 8

On-Line Outliers

Answer 8

Outliers that fall in the same pattern as the rest of the data and tend to artifically inflate r.

Question 9

Off-Line Outliers

Answer 9

Outliers that fall outside of the pattern of the rest of the data and tend to artifically deflate r.

Question 10

How can the reliability of a measure affect r?

Answer 10

The less reliable a measure is, the lower its correlations with other measures will be.

Question 11

Spurious Correlation

Answer 11

Correlation between two variables due to their relation to other variables.

Question 12

Criteria for Inferring Causality

Answer 12

1. Covariation: Changes in one variable are associated with changes in the other variable.
2. Directionality: The presumed causal variable preceded the presumed effect in time.
3. Extraneous Variables: All other variables that may affect the relationship between the two target variables are controlled or eliminated (correlational research can never satisfy this criterion).

Question 13

Partial Correlation

Answer 13

The correlation between two variables with the influence of one or more other variables statistically removed. If a partial correlation between two variables (with the influence of a third variable removed) is significantly lower than the Pearson correlation between the two variables, then the correlation between them is at least partly due to the third variable (or to a variable associated with the third variable).

Question 14

Zero-Order Correlation

Answer 14

Just the correlation between X and Y without any other variables.