Back to Glossary
Glossary
When too many respondents score at or near the maximum, the assessment can't distinguish between them or detect further increase.
A ceiling effect occurs when too many respondents score at or near the maximum possible value on an assessment, so the test can no longer distinguish between them. If a depression screener tops out at 20 and many respondents in a clinical sample score 18–20, the instrument can't tell their severity apart or detect whether they're getting worse.
Ceiling effects also limit the ability to measure improvement over time. They're especially common in screening tools used in populations the tool wasn't designed for — for example, a general-population screener used in a severely affected clinical sample. The mirror-image problem is the floor effect.