A correlation analysis is used to provide a numeric value for which of the following types of relationships between two variables?

Question

Options

• ARandom
• BLinear
• CCurvilinear
• DCausation

• A
  4% (1)
• B
  86% (24)
• C
  4% (1)
• D
  7% (2)

Explanation

Correlation analysis quantifies the strength and direction of linear relationships between two variables, producing a value (r) between -1 and +1 that describes how closely the data points follow a straight line. Option A is wrong because random relationships have no pattern to measure - correlation would be near zero, but that's a result, not the type of relationship correlation is designed to describe. Option C is wrong because while curvilinear relationships exist, Pearson correlation specifically measures linear fit; a strong curve can produce a misleadingly low r value. Option D is wrong because correlation measures association, never causation - two variables can be perfectly correlated without one causing the other.

Memory tip: Think of the "r" in correlation as standing for "ruler" - a ruler only measures straight lines, just as correlation only captures linear relationships.

No community discussion yet for this question.