What is the a-value? Statistical analyses help you create a good (digital) test. One of the statistical concepts you can use is the a-value. But what exactly is the a-value of a question? And how useful is the a-value in a (digital) test? What is the a-value? The a-value is the percentage (or proportion) of candidates who choose a distractor for the question. A multiple-choice question has several answer options. In addition to the correct answer, there are a number of ‘distractions. As a tool, the a-value enables you to measure the quality of the distractors. Each distractor in the test has its own a-value. This a-value represents the proportion of candidates who choose this distractor. There is a clever mnemonic device to help you remember what the A value stands for. You can think of the A value as the ‘Afleider value. Item-level analyses A (digital) summative assessment aims to make a final assessment. As an examination board or educational institution, you naturally want to measure knowledge and insights as accurately as possible. You want the results of a test to accurately reflect which candidates have prepared well and which have prepared less well. It is therefore wise to view and analyse statistical data at item level. A useful statistical variable is the a-value, which provides insight at item level and enables you to improve the quality of items. Example Suppose you have an exam with 20 multiple-choice questions. It may be that not every question is equally strong in terms of testing technique. By making the a-value transparent, you know what percentage of candidates choose a distractor. An example question is as follows: Question: What colours does the Optimum Assessment logo have? Blue and green Yellow and black Red and black Red and Yellow Answer 3 is correct and is the ‘key answer’. The other answers (1, 2 and 4) are distractors. Suppose that the statistical analyses show that answer option A is rarely chosen by candidates. In that case, the answer option does not fit the question well. Probability score As a result, the chance score increases. The chance score is the score a candidate can achieve if they guess the correct answer, but do not actually know it. An item with a low a-value contributes to your test being a less accurate reflection of your candidates' level of knowledge. In that case, you can choose to change the distractor. A-value between 0 and 1 The a-value is between 0 and 1. Suppose you have one correct answer option that is chosen by half of the exam candidates, then there is still a value of 0.5 that is divided between the distractors. You therefore always calculate an a-value based on answer options. More inspiration Would you like to learn more about the a-value or other statistical data related to digital testing? Take a look at our knowledge base. You can also register for our newsletter or Follow us on LinkedIn to stay informed about developments in digital testing.
