Skip to main content

Table 3 Parameter estimates (standard errors) of request networks

From: Exchanging and using research evidence in health policy networks: a statistical network analysis

  Child health Malaria HIV
  Structural effects model Attribute effects model Full model Structural effects model Attribute effects model Full model Structural effects model Attribute effects model Full model
Structural effects    
Edge intercept -4.00 (0.997)* -1.47 (0.406)* -4.67 (1.15)* -3.66 (0.545)* -2.64 (0.787)* -4.19 (1.19)* -3.37 (0.743)* -5.83 (1.92)* -6.74 (2.21)*
Triangle closure 1.49 (0.812)* __ 1.53 (0.848)* 1.26 (0.601)* __ 1.65 (2.88) nf __ nf
Reciprocity -1.93 (1.49)* __ -1.90 (1.62) 0.029 (1.28) __ -1.43 (1.49) 1.98 (1.34) __ -0.842 (2.14)
Layering 2.72 (1.12)* __ 2.96 (1.14)* 3.28 (0.604)* __ 3.18 (0.733)* 2.27 (0.832)* __ 2.31 (0.992)*
Attribute effects    
Researcher __ 0.088 (0.401) 0.652 (0.486) __ 1.90 (0.473)* 1.73 (0.688)* __ 1.70 (0.901)* 1.64 (1.01)
Civil society org. __ nf nf __ -0.490 (0.498) -0.313 (0.593) __ 1.30 (0.731)* 1.31 (0.788)
Development partner org. __ nf nf __ -2.29 (0.979)* -3.34 (1.41)* __ nf nf
Other __ nf nf __ -0.407 (0.944) -1.27 (1.21) __ 2.32 (0.953)* 1.85 (1.10)*
Manager/director __ nf nf __ 0.619 (0.379) 0.613 (0.478) __ nf nf
Homophily    
Researcher __ nf nf __ nf nf __ nf nf
Organization __ nf nf __ -1.60 (0.663)* -2.24 (0.933)* __ nf nf
AIC 183.4 208.7 183.5 310.6 334.7 306.9 162.7 171.6 DNC
  1. *p < 0.05; nf = term did not improve model fit.