How do actuaries use data containing errors?: Models of error detection and error correction

Abstract

Information systems provide data for business processes and decision making. There is strong evidence that data items stored in organizational databases have a significant rate of errors. If undetected in use, errors in data may significantly affect business outcomes. The question examined in this paper is the extent to which business professionals are able to evaluate the quality of data in the information systems they use and the impact of their evaluations on decision-making behavior. Models of error detection and error correction processes are developed. The validity of the models is then examined through an analysis of interviews with ten actuaries. The findings show that actuaries detect errors in data using three general methods and that actuaries consider feasibility and costs when deciding whether to correct data errors.