Modifications of the Stringer bound: A simulation study on the performance of audit sampling evaluation methods

This paper presents three modifications of the Stringer bound in audit sampling evaluations. The behavior of the Stringer bound and of the suggested modifications is studied by means of simulation. Two of the modifications proposed seem to yield better upper bounds for the misstatement percentage in a population: they satisfy the nominal confidence level and result in an upper bound below the Stringer bound. The modification Amount Tainting Order (ATO) is preferred by the authors. * Deloitte & Touche Computer Assurance Services Center P.O. Box 5814