A Data-Driven Hybrid Three-Stage Framework for Hospital Bed Allocation: A Case Study in a Large Tertiary Hospital in China

Table 11

Relationship between beds and BOR in W6.

Function	Model					Parameters
	R^2	F	df1	df2	Sig.	Constant	b1	b2	b3
Linear	0.664	21.741	1	11	0.001	1.118	−0.002
Logarithm	0.558	13.883	1	11	0.003	1.616	−0.147
Quadratic	0.956	107.465	2	10	0.000	0.687	0.008	−4.932E − 5
Composite	0.645	19.978	1	11	0.001	1.140	0.998
Power	0.539	12.849	1	11	0.004	1.966	−0.161
Growth	0.645	19.978	1	11	0.001	0.131	−0.002
Exponential	0.645	19.978	1	11	0.001	1.140	−0.002
Logistic	0.645	19.978	1	11	0.001	0.877	1.002

Note. The higher the R², the better the function model. When the W6 model is fitted, it has the same outcome as W9. The quadratic curve is also selected. The bed number of W6 is C₃, and the bed rate is BOR₃ (C₃). According to the estimated value of the parameter, .