This article focuses on how regression analysis, coupled with Bayesian statistical procedures, can be used to provide assistance to auditors in selecting accounts for investigation. Auditors characteristically express their opinion on corporate financial statements on the basis of an examination of only a small portion of the underlying data. Often the auditor relies on little more than informed judgment as to the specific data that he should review. In examining some accounts, notably inventory and accounts receivable, statistical sampling methods are sometimes used to select the data to be studied in detail. Frequently however, the auditor must operate with relatively little guidance as to which particular accounts or subaccounts merit comprehensive review. The purpose of this article is to demonstrate how regression analysis, coupled with Bayesian statistical procedures, can be used to provide the auditor with assistance in selecting those accounts for investigation that are most likely to result in significant audit findings.

This article presents comments on an article written by M.E. Francis, published in the April 1973 issue of the journal "The Accounting Review," which contends that accountants are ill-equipped to contribute in a constructive way either to improve the methods of assessing the state of society and social programs or to the application of evaluative procedures in the allocation of resources to the efforts to improve social well-being. The article provides a useful service to the profession by cautioning accountants against jumping upon the social accounting bandwagon without knowing its ultimate destination or their own ability to steer it in an appropriate direction. The argument of Francis against a potential role for accountants is three-fold: accountants lack the expertise to attest to sampling methods and statistical series derived from samples; accountants do not have the knowledge or experience to determine the relevant statistical information to be collected, analyzed, and reported; and accountants lack the statistical training to improve the accuracy of economic data. The accountant, as a member of a team which is likely to include specialists from other disciplines, independently appraises program results and reports his findings to the policy makers. Contrary to the implications of Francis, accountants seldom, if ever, work with numbers that are finitely accurate.

This article describes a taxonomy of cognitive skills which has been designed by a group of educational psychologists and identifies the implications thereof for the development of accounting courses and the accounting curriculum. The taxonomy is designed to give precise direction to the learning process and is expressed in terms of expected student behavior at each level in the accounting program. The primary focus of this paper is on the financial accounting program. The taxonomy is relevant to the development of curriculum in that it reveals the elements in the learning process, orders them in an educationally logical sequence, and helps explain the interrelationships among them. It raises questions not only of what should be taught, but also of when and why it should be taught.