Skip to main content
Fig. 3 | BMC Public Health

Fig. 3

From: Predicting medical usage rate at mass gathering events in Belgium: development and validation of a nonlinear multivariable regression model

Fig. 3

Multivariable regression tree for TTHR. Each square contains the hierarchical number of the split and the name of the splitting variable (MG cat.: MG category; node: number of terminal node in the PPR model, see Fig. 1; attend: attendance). CF: city festival; IE: indoor EDM; ID: indoor dance; OE: outdoor EDM; OM: outdoor music; SE: sports event. Each blue circle contains the number of the terminal node. Numbers in bold indicate the predicted TTHR per 10,000 visitors for each terminal node (mean ± standard deviation) and the number of MGs (n) in this node

Back to article page

BMC Public Health

ISSN: 1471-2458

Contact us