This paper describes two procedures for making binary classification decisions using tailored testing: the sequential probability ratio test (SPRT) and a Bayesian decision procedure. The first procedure described, the SPRT, was developed by Wald for quality control work. It has not been widely applied for testing applications because the assumption of an equal probability of a correct response was made to facilitate the derivation of the operating characteristic (OC) and average sample number (ASN) functions. The results of the application of the SPRT with a simulated procedure are described. The second decision procedure, the Bayesian procedure, includes a prior distribution of student achievement, a loss function for incorrect decisions, and the cost of observations in the development of the decision rule. The basic philosophy of this procedure is to administer items until the expected loss incurred in making a decision is less than the expected loss after the next item is administered plus the cost of administration. This procedure is not yet operational for making decisions under tailored testing because appropriate loss functions for educational decisions have not been determined. (Author/BW)