Latent trait test score theory is discussed primarily in terms of Birnbaum's three-parameter logistic model, and with some reference to the Rasch model. Equations and graphic illustrations are given for item characteristic curves and item information curves. An example is given for a hypothetical 20-item adaptive test, showing cumulative results of ability estimates for one candidate under four methods: maximum likelihood estimates; weighted by likelihoods estimates; simplified Bayesian estimates; and Owen's normal ogive Bayesian estimates. Finally, information curves are given comparing a hypothetical 20-item adaptive test with information curves for a test with a broad rectangular item-difficulty distribution and a test with a peaked item-difficulty distribution. (CTM)