Before generation
Use this after a quiz to identify items that may be too easy, difficult, miskeyed, ambiguous, poorly taught, or weak at separating the supplied upper and lower groups.
EDUCATION DECISION WORKBENCH
Quiz Difficulty Analyzer
Calculate item facility and upper-lower discrimination with transparent review thresholds.
Runs in this browser tabEditable downloadUp to 500 structured rows and 30,000 characters per field. Use anonymous or fictional labels.
Review output
Your learning artifact appears here
Load the worked example to inspect realistic inputs, or enter anonymous, policy-approved information. Results remain in this browser tab until you copy or download them.
Transparent method
How the quiz difficulty analyzer works
Facility p = correct ÷ attempts. Group size = round(0.27 × attempts). Upper-lower discrimination D = (upper correct − lower correct) ÷ group size. Flags are review prompts. Easy items can be appropriate for essential knowledge, and difficult items can expose teaching opportunity or wording problems. Inspect the item and evidence.
- 01Before generation
Prepare anonymous aggregate item totals.
- 02During review
Inspect facility, discrimination, key, distractors, and wording.
- 03Before use
Document any item change and avoid comparing scores across materially different forms without review.
How to interpret the result
Quiz Difficulty Analyzer
Worked example
With 28 attempts, the tool models a 27% group as eight learners. An item with 17 correct has facility 0.61; if seven upper-group and three lower-group learners are correct, discrimination is 0.50.
Formula or methodology
Facility p = correct ÷ attempts. Group size = round(0.27 × attempts). Upper-lower discrimination D = (upper correct − lower correct) ÷ group size.
How to interpret the result
Flags are review prompts. Easy items can be appropriate for essential knowledge, and difficult items can expose teaching opportunity or wording problems. Inspect the item and evidence.
Common mistakes
Do not reverse difficulty labels, use unequal upper and lower groups, treat a negative value as learner failure, or revise an item without checking the key and curriculum alignment.
Learning boundary
Statistics do not validate an item
Small samples are unstable. Qualified educators must review content, opportunity to learn, accessibility, scoring, and use of results.
Review checklist
Human review before educational use
- Attempts and correct counts are accurate.
- Upper and lower groups are equal.
- Keys and distractors are reviewed.
- Changes are documented before reuse.
Practical questions
Quiz Difficulty Analyzer questions
Is a high facility value difficult?
No. Facility is the proportion correct, so a high value usually means easier for this group.
What does negative discrimination mean?
The lower group outperformed the upper group on that item; inspect the key, wording, content, and sample.
What threshold should I use?
Use local assessment guidance and context; the entered thresholds are review preferences.