Test validity is a concept that has often been ignored in the context of latent trait models and in modern test theory, particularly as it relates to computerized adaptive testing. Some considerations about the validity of a test and of a single item are proposed. This paper focuses on measures that are population-free and that will provide local and abundant information just as the information functions do in comparison with the test reliability coefficient in classical mental test theory. In so doing, validity indices for different purposes of testing and those that are tailored for a specific population of examinees are considered. The resulting indices should not be incidental as those in classical mental test theory are; they are truly attributes of the item and the test. Six figures illustrate the discussion. (Author/SLD)