Item analysis is a method used to evaluate the quality of individual test questions or items in an assessment. The goal of item analysis is to identify questions or items that are functioning well and those that are not, in order to improve the overall quality of the assessment.
During item analysis, various statistics are calculated for each item, such as difficulty index, discrimination index, and point-biserial correlation coefficient. These statistics provide information about the item’s performance, such as how well the item is measuring what it is supposed to measure, and how well it is discriminating between high and low performers.
There are different types of item analysis, but some common methods include:
1. Difficulty index
This measures the proportion of test-takers who answered the item correctly. A difficulty index of 0.50 means that about half of the test-takers answered the item correctly.
2. Discrimination index
This measures how well the item is able to distinguish between high-performing and low-performing test-takers. A positive discrimination index indicates that high-performing test-takers tend to answer the item correctly more often than low-performing test-takers.
3. Point-biserial correlation coefficient
This measures the correlation between the test-takers’ overall scores on the assessment and their scores on the individual item. A high point-biserial correlation coefficient indicates that the item is a good measure of the overall construct being assessed.
Item analysis helps to identify items that need improvement and to improve the overall quality of the assessment. It can also help to identify questions that are too easy or too hard, or that are not providing useful information. Based on the results of the item analysis, items can be revised, replaced, or eliminated. It’s worth noting that item analysis is one of the many tools used to evaluate the quality of assessments and is used along with other methods such as content validity, criterion-related validity, and construct validity.
