Abstract In the quest for a more efficient way of reducing auditing costs, certified public accountants have become interested in statistics. They contend that if this statement is taken literally, a rigorous sampling requirement is imposed. Only through the application of statistical sampling techniques of the highest order could such a desirable objective be achieved. Many of the problems associated with the current use of statistics would be overcome. The question of the significance of a particular percentage of errors to the quality of the accounts involved would be avoided. The purpose of the test would be clearly established, enabling the audit supervisor adequately to plan and instruct his subordinates, tables and charts could be prepared. The use of the computer itself could aid in drawing the random sample of accounts to be circularized as an illustration, reducing human error. The tests would be simpler and more uniform when divorced from internal control. "Exploratory" sampling or error finding would not be the objective.
Mogis et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: