Investment management is a decision-making process which ranges from an individual managing his own small portfolio of securities to institutional investors who manage portfolios valued in millions of dollars. The importance of investment management is readily observed in the increased activity of the securities markets, the close scrutiny given by regulatory agencies to various institutional investors and professional investment managers, the growing market value of pension funds, trust funds, and investment companies, and finally, the increasing number of related research studies which are reported in the financial literature.

The article focuses on the relation of accounting and operation research (OR). There has been an unresolved disagreement in the accounting profession as to the accountant's role in OR. In this article the author attempts to clarify what is meant by operations research and examines what are felt to be the logical implications of OR for the accounting profession. There are several phrases which have been used frequently in attempting to define OR. The author defines it as the scientific method to the development of predictive models which describe the stable patterns of order underlying certain business operations and thereby enabling the provision of quantitative information which is helpful in solving executive-type problems. There are three basic views which currently prevail concerning the relationship of accounting and operations research. At one extreme is the view that OR is entirely subsumed by accounting. On the other extreme is the view that accounting is relatively unaffected by OR. The third view is the middle-of-the-road view.

In this paper, the exact posterior distributions of the parameters of Haavelmo's model I is derived for locally uniform prior distributions. Marginal distributions of the parameters have been obtained for Haavelmo's data. Then the predictive probability density of the model is derived for given values of the exogenous variable, investment. In order to check some of the specifying assumptions, the model is expanded and analyzed under the assumption that the error terms are generated by a first order autoregressive scheme. Exact finite sample results are obtained and the posterior distributions are computed for Haavelmo's data. Conditional distributions of the parameters of the model are computed for given values of the autocorrelation parameter, p, in order to assess the effects of departures from our specifying assumptions. Another specifying assumption that is examined concerns the exogenous nature of investment. For this. Haavelmo's model II, in which investment is assumed to be endogenous, is used. Posterior distributions of the parameters of the model are computed for this model. The sensitiveness of the inference about the parameters of the model to the assumption that investment is exogeneous is studied by computing various conditional distributions for model II. It is seen that this assumption is very crucial for Haavelmo's data. Finally, tvAo different pr-ior distribLutions reflecting two different views about investmeint are introduced. The posterior distributions of the same parameter are then used to determille how one's prior belief is modified by the sample information.