What is it about?
The objective of this study was to validate the application of the Decision Tree technique to archival NTSB accident data, to yield a better tool than simple correlational analysis for preventing loss of life and property due to airborne icing encounters.
Featured Image
Photo by erin mckenna on Unsplash
Why is it important?
This would have important practical consequences for future researchers. This is because decision trees have a very useful property of identifying potential causal relationships between the variables, based on the tree structure automatically generated by the analysis, which differentiates the decision tree method from simple correlational methods (such as linear regression techniques), which rely entirely on the researcher to differentiate between causality and correlation.
Read the Original
This page is a summary of: Validation of Decision Tree Methods in Predictive Analysis of Airborne Icing Incidents, Journal of Aerospace Computing Information and Communication, November 2017, American Institute of Aeronautics and Astronautics (AIAA),
DOI: 10.2514/1.i010542.
You can read the full text:
Contributors
The following have contributed to this page
