Estimation of the Allowance for Doubtful Accounts by Markov Chains

Investigation of more accurate and efficient methods of estimating the allowance for doubtful accounts was begun in the early 1950's by R. M. Cyert and R. M. Trueblood [Cyert, R. M., R. M. Trueblood. 1957. Statistical sampling techniques in the aging of accounts receivable in a department store. Management Sci. 3 (2, January) 185-195.]. At this time, studies were confined primarily to investigation of more efficient methods of performing the first step in the estimation procedure: determining the age distribution of accounts. In particular, the applicability of statistical sampling techniques was evaluated. A number of retail establishments now use scientific sampling methods to perform the first step in the estimation of the allowance for doubtful accounts. As a continuation of research, the second phase of the allowance estimation problem was a logical area for investigation. While it did not seem likely that all of the judgment factors involved in the setting of loss expectancy rates could be eliminated, it did appear feasible to develop a scientific approach to determining these rates. Accordingly, research into this problem was initiated. This paper discusses a method which has been developed. In addition, some of the managerial implications of the method are discussed.