What is the purpose of a validity coefficient, and what is a commonly used statistic to quantify validity evidence?

• A. To quantify how well a test measures the intended construct; correlation with an external criterion is common.
• B. To measure reliability across time.
• C. To assess the difficulty of items.
• D. To determine test length.

Answer: (A)

Validity is about whether a test actually measures what it’s meant to measure. The validity coefficient captures how strongly test scores relate to an external criterion that the test should predict or align with, providing evidence that the test measures the intended construct. The most common statistic used to quantify this evidence is the correlation between the test scores and that external criterion (typically the Pearson correlation). A strong positive correlation means higher test scores are associated with higher criterion performance, supporting validity. For example, a new employment aptitude test would be considered to have good validity if its scores closely track actual job performance ratings. This focus on the relationship to an external criterion distinguishes validity from other properties like reliability, item difficulty, or test length.