What does effect size quantify, and which two measures are commonly used?

• A. The probability of observing the data if the null is true.
• B. Quantifies the magnitude of a relationship or difference; Cohen's d and Pearson's r are common.
• C. Measures sampling error alone.
• D. Represents the chance of making a Type I error.

Answer: (B)

Effect size quantifies the magnitude of a relationship or difference, giving a standardized sense of how big the observed effect is. The two commonly used measures are Cohen's d and Pearson's r. Cohen's d expresses the difference between two group means in units of standard deviation, making it easy to compare effects across studies and scales. Pearson's r captures the strength and direction of a linear association between two variables, ranging from -1 to 1. These metrics focus on practical significance rather than whether an effect exists, which is what p-values address. For example, a study might find a statistically significant difference with a tiny p-value due to a large sample, but the effect size could be very small and potentially not practically important. That’s why effect size is about how big the effect is, not just whether it’s likely to occur by chance. The other statements describe probabilities or error rates (p-value, sampling error, Type I error) rather than the size of the effect.