Skip to main content

Table 2 Fit Statistics for Confirmatory Factor Analyses and Structural Models

From: The role of psychological safety and learning behavior in the development of effective quality improvement teams in Ghana: an observational study

Model Description Number of: DF χ2
(p-value) a
RMSEA
(Pr ≤ 0.05)
CFI BICsb
Observations (Teams) Latent Variables Observed Variables Free Parameters
CFA:
LEAD with SUPPORT
127 2 7 23 12 17.0
(0.149)
0.057
(0.376)
0.983 −41.1
CFA:
SAFETY with LEARN
127 2 8 26 18 42.8
(0.001)
0.104
(0.016)
0.919 −44.4
CFA:
QI Implementation
122 1 6 19 8 5.7
(0.677)
0.000
(0.828)
1.000 −32.7
Structural Model: Complete Mediationc 122 5 26 113 264 403.7
(< 0.001)
0.066
(0.025)
0.920 − 864.6
Structural Model: Complete Mediationd 122 5 26 116 261 371.7
(< 0.001)
0.059
(0.142)
0.936 −882.1
Structural Model: Partial Mediationd 122 5 26 121 256 360.8
(< 0.001)
0.058
(0.175)
0.940 −869.0
  1. Notes: χ2 is more likely to reject fit with larger N and more variables
  2. RMSEA is more likely to reject fit with smaller N and lower DF
  3. BICs < 0 indicates good model fit. When comparing similar models, the more negative BIC indicates better fit
  4. a Scaled χ2 [56]
  5. b Schwarz BIC [47]
  6. c Model includes no correlated errors
  7. d Model includes three correlated errors based on a priori expectations