What is the trip value of a question? If you want to make a good test, statistical analysis is essential. One of the statistical measures that says something about an exam question is the trip value. But what exactly is a trip value? And how does a trip value fit into the process of digital testing? What does the ride value stand for? Despite the fact that we write rit-value in lower case, it is actually an acronym/letter word. Namely, RIT stands for: R - Correlation I - Item score T - Overall score In testing jargon, the ride value means: the correlation (r) between the item score (i) and the total score (t). What is a trip value? A ride value indicates how well the item individually, measures the same as the test as a whole. In other words, how well the item in question fits into the test. The ride value shows how the item makes a difference between candidates with high scores on the test and those with low scores on the test. Thus, the ride value indicates the distinctiveness of the item. Combined demand analysis (p and trip values) If you take the p-value (read also: what is the p-value?) and the trip value against each other in a graph, you can see which items need to be critically assessed. The items in the red areas should at least be scrutinised. Notice in the figure below that there are very many easy items (high p-values). Combined demand analysis - p-value and trip value A high or a low ride value? The standard of an acceptable trip value varies widely. In the literature, the following standards are generally used (Veldhuijzen, Goldebeld & Sanders, 1993). As a side note, the standards below are only guidelines that may vary from one situation to another. 40 and above - very good 30 - 0.39 - good 20 - 0.29 - doubtful 19 and below - bad More inspiration Want to learn more about trip value or other statistics 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.
