This paper describes major concepts related to item analysis for criterion-referenced tests including validity, reliability, item difficulty, and item discrimination, particularly in relation to criterion-referenced tests. The paper discussed how these concepts can be used to revise and improve items and listed suggestions regarding general guidelines for test development. The paper concluded with a brief discussion of standard setting, latent trait theory, item response theory, and differential item functioning. (Contains 11 tables.) [Funding is provided by the New York State Office of Children and Family Services.]