AI Summary & Key Takeaways
AI InsightAdditionally, the BLR model concluded that when the age of the victim increased by one unit, victims are 1.068 times more likely to have a major workday loss, and similarly, when the height of falling increases by one unit, victims are 1.735 more likely to have a major workday loss.
📌 3 Key Takeaways
Abstract
The study aims to build a model for workday losses due to scaffolding accidents at construction sites to know information about the worker and the accident, and subsequently use the model for prediction, process optimization, or process control. The accident investigations from the archive of the Labour Office were searched and ongoing construction sites in North Cyprus were visited. Descriptive statistics were used to classify the full archival and inferential statistics were carried out to construct a statistical model using multiple linear regression (MLR) analysis to predict future workday losses furthermore binary logistic regression (BLR) model was carried out to identify whether the workday loss is considered to be a major workday loss or not. MLR model revealed that a 4.5-fold increase in workdays lost for each additional 1 meter of fall height and one year increase in workers’ age will increase the workday losses by 1.3 days. Additionally, the BLR model concluded that when the age of the victim increased by one unit, victims are 1.068 times more likely to have a major workday loss, and similarly, when the height of falling increases by one unit, victims are 1.735 more likely to have a major workday loss.