We analyze a 12-item version of Raven's Standard Progressive Matrices test, traditionally scored with the sum score. We discuss some important differences between assessment in practice and psychometric modelling. We demonstrate some advanced diagnostic tools in the freely available R package, dexter. We find that the first item in the test functions badly-at a guess, because the subjects were not given exercise items before the live test.
Keywords: IRT; classical test theory; intelligence tests; interaction model; test-item regression.