Table 5.

Ordered logistic regression results in unrestricted (full) and restricted (reduced) models highlighting the factors explaining the outlook of the private green industry on the urban forestry (UF) business.

VariableFull ordered logistic model (N = 346)Restricted generalized ordered logistic model (N = 349)
Coefficient (standard error)P-value (P > [z])Coefficient (standard error)P-value (P > [z])Odds ratio
landscaping0.17 (0.31)0.580.46 (0.22)0.041.58
nursery supply−1.96 (0.72)0.00−1.73 (0.67)0.010.18
nursery tree−0.37 (0.42)0.38
nursery stores−0.17 (0.46)0.72
architecture−0.26 (0.38)0.49
Log (jobs)0.14 (0.09)0.110.13 (0.08)0.091.15
Log (longevity)−0.18 (0.15)0.24
UF jobs0.02 (0.01)0.00−0.01 (0.01)a0.170.98
corporate0.37 (0.22)0.090.36 (0.21)0.091.43
R&D0.25 (0.13)0.050.20 (0.12)0.081.22
supply chain−0.10 (0.13)0.43
recruitment0.08 (0.11)0.46
retention−0.06 (0.12)0.63
The likelihood ratio test of proportionality of odds67.640.0012.540.56
  • a The Gamma function in the generalized ordered logistic regression produces 4 Gamma coefficients for the variables that deviate from proportionality. So, UF jobs has Gamma 2 value of 0.02 (0.01), Gamma 3 value of 0.04 (0.01), and Gamma 4 value of 0.04 (0.01). All 3 Gamma estimates are statistically significant.