Which statement describes Spearman's correlation coefficient?

Which statement describes Spearman's correlation coefficient?

• A. A standardized measure of the strength of the relationship that relies on the assumptions of a parametric test.
• B. A measure that uses raw scores without ranking.
• C. A standardized measure of the strength of the relationship that does not rely on parametric test assumptions; it is Pearson's correlation performed on ranked scores.
• D. A test for equality of variances.

Answer: (C)

Spearman's correlation coefficient is a nonparametric measure of rank correlation. It gauges how well the relationship between two variables can be described by a monotonic function by ranking the data for each variable and then computing the Pearson correlation on those ranks. Because it uses ranks, it does not rely on parametric test assumptions like normality or linearity, making it suitable for ordinal data or outliers. The described statement fits best: a standardized measure of the strength of the relationship that does not rely on parametric test assumptions; it is Pearson's correlation performed on ranked scores. The other options describe aspects that don’t apply to Spearman’s rho—the reliance on parametric assumptions, the use of raw scores without ranking, or a different test for variances.

Spearman's correlation coefficient is a nonparametric measure of rank correlation. It gauges how well the relationship between two variables can be described by a monotonic function by ranking the data for each variable and then computing the Pearson correlation on those ranks. Because it uses ranks, it does not rely on parametric test assumptions like normality or linearity, making it suitable for ordinal data or outliers. The described statement fits best: a standardized measure of the strength of the relationship that does not rely on parametric test assumptions; it is Pearson's correlation performed on ranked scores. The other options describe aspects that don’t apply to Spearman’s rho—the reliance on parametric assumptions, the use of raw scores without ranking, or a different test for variances.