Validity
This term describes how well a test measures what it claims to measure
What is validity?
If a test gives students the same score again and again, but the score is wrong, it illustrates this danger of relying on reliability alone.
What is high reliability without validity?
A classroom quiz that uses poorly written questions might produce inconsistent scores, harming this important testing quality.
What is reliability?
Random factors—like a student being tired or distracted—that affect a student’s test score fall under this kind of measurement error.
What is systematic error?
Popham says this is the most important consideration in testing because it tells us whether our conclusions based on test scores are accurate.
What is validity evidence?
This type of reliability checks whether multiple graders score a student response the same way.
What is inter-rater reliability?
Teachers rely on test results to place students in groups or identify who needs support. This is why this form of test evidence must come before all others.
What is validity evidence?
A test written with confusing directions or misleading questions introduces this kind of threat to reliability.
What is item-related error?
A spelling test that ends up measuring handwriting neatness instead is suffering from this major validity issue.
What is construct-irrelevant variance?
This term refers to the consistency of test scores across time, forms, or raters.
What is reliability?
This tool helps teachers score performance tasks consistently, improving reliability.
What is a rubric?
This technical term describes the gap between a student’s true score and obtained score.
What is measurement error?
This type of validity asks whether the test content actually matches the skills or knowledge being assessed.
What is content validity?
According to Popham, a test cannot be valid without being at least somewhat this.
What is reliable?