In continuous improvement (CI) projects, cause-and-effect diagrams are used to qualitatively express the relationship between a given problem and its root causes. However, when data collection activities are limited, and advanced statistical analyses are not possible, practitioners need to understand causal relationships. The paper aims to discuss these issues.
In this research, the authors present a framework that combines cause-and-effect diagrams with Bayesian belief networks (BBNs) to estimate causal relationships in instances where formal data collection/analysis activities are too costly or impractical. Specifically, the authors use cause-and-effect diagrams to create causal networks, and leverage elicitation methods to estimate the likelihood of risk scenarios by means of computer-based simulation.
This framework enables CI practitioners to leverage qualitative data and expertise to conduct in-depth statistical analysis in the event that data collection activities cannot be fully executed. Furthermore, this allows CI practitioners to identify critical root causes of a given problem under investigation before generating solutions.
This is the first framework that translates qualitative insights from a cause-and-effect diagram into a closed-form relationship between inputs and outputs by means of BBN models, simulation and regression.
