A structured approach to systems testing
A structured approach to systems testing
Data quality and due process in large interorganizational record systems
Communications of the ACM
Not all answers are equally good: estimating the quality of database answers
Flexible query answering systems
Estimating and improving the quality of information in a MIS
Communications of the ACM
Data Quality for the Information Age
Data Quality for the Information Age
Sample-Based Quality Estimation of Query Results in Relational Database Environments
IEEE Transactions on Knowledge and Data Engineering
| Hi-index | 0.00 |
This inquiry centers on an asymmetry, or bias, in the accuracy of multi-criteria, conjunctive, and disjunctive decisions, which originates from fundamental properties of the logical conjunction and disjunction operations. A mathematical-statistical analysis indicates that, as we keep adding criteria to a multi-criteria conjunctive or disjunctive decision rule, errors in the data produce decision errors asymmetrically. As a result, in conjunctive decisions, the probability of a false negative increases while the probability of a false positive decreases. In contrast, in disjunctive decisions, as we keep adding criteria, the probability of a false positive increases while that of a false negative decreases. For instance, in a conjunctive business decision rule, the probability of overlooking a bargain can be far greater than the probability of misjudging an unattractive offer to be a good one. A series of Monte Carlo simulations validates the analytical findings and explores the contribution of several additional factors.