Psychometricians love data. We were doing “data science” long before the term was cool. In fact, one of the major MOOC courses on Data Science (Johns Hopkins) starts out by using a psychometric approach called factor analysis (Spearman, 1904) as a shining example of early data science!
So, what kind of analysis do we do? Evaluate the performance of items and tests by looking at key statistics as well as fitting complex models like item response theory. This helps you improve your content, as well as serving as validity documentation. This, in turn, makes your assessment stronger, more accurate, more effective, and more defensible.