Optimal Item Difficulty
“Item difficulty” is the percentage of the total group that got the item correct. See the Total column listed under Correct Group Responses on the attached report.
Item difficulty is important because it reveals whether an item is too easy or too hard. In either case, the item may add to the unreliability of the test because it does not aid in differentiating between those students who know the material and those who do not. For example, an item answered correctly by everyone does nothing to aid in the assignment of grades. The same is true for items that no one answers correctly.
The optimal item difficulty depends on the question-type and on the number of possible distractors. Many test experts believe that for a maximum discrimination between high and low achievers, the optimal levels (adjusting for guessing) are:
Item Difficulty:
2 alternatives true and false = .75
3 alternatives multiple-choice = .67
4 alternatives multiple-choice = .63
5 alternatives multiple-choice = .60
Items with difficulties less than 30% or more than 90% definitely need attention. Such items should either be revised or replaced. An exception might be at the beginning of a test where easier items (90% or higher) may be desirable.
Item difficulty is important because it reveals whether an item is too easy or too hard. In either case, the item may add to the unreliability of the test because it does not aid in differentiating between those students who know the material and those who do not. For example, an item answered correctly by everyone does nothing to aid in the assignment of grades. The same is true for items that no one answers correctly.
The optimal item difficulty depends on the question-type and on the number of possible distractors. Many test experts believe that for a maximum discrimination between high and low achievers, the optimal levels (adjusting for guessing) are:
Item Difficulty:
2 alternatives true and false = .75
3 alternatives multiple-choice = .67
4 alternatives multiple-choice = .63
5 alternatives multiple-choice = .60
Items with difficulties less than 30% or more than 90% definitely need attention. Such items should either be revised or replaced. An exception might be at the beginning of a test where easier items (90% or higher) may be desirable.
Comments