Table 6

Regression results on the affective appeal profile (dependent variable: AAP)

Model 1Model 2Model 3Model 4Model 5Model 6
Constant0.276* (0.159)0.062 (0.158)0.271* (0.159)0.264 (0.162)0.298* (0.158)0.268* (0.157)
BPOWER0.002* (0.001)0.003*** (0.001)0.002 (0.001)0.002* (0.001)0.001 (0.001)0.002* (0.001)
AREA_RELIG−0.022 (0.018)0.031 (0.021)−0.02 (0.018)−0.02 (0.018)−0.027 (0.018)−0.028 (0.018)
ROA−75.133* (38.109)−64.008* (35.834)−81.78** (38.571)−75.769* (38.274)−67.408* (38.081)−82.894** (37.863)
RELIG6.829*** (1.012)3.267** (1.284)6.082*** (1.224)6.97*** (1.07)6.386*** (1.038)6.505*** (1.014)
COOP5.854 (9.232)1.821 (8.712)5.664 (9.227)6.344 (9.338)2.355 (9.389)5.553 (9.123)
RELIG × AREA_RELIG 1.013*** (0.246)    
RELIG × BPOWER  −0.015 (0.014)   
COOP × AREA_RELIG   −0.602 (1.424)  
COOP × BPOWER    0.131* (0.077) 
RELIG × COOP     179.559* (91.896)
R-Sq0.3530.4370.360.3540.3690.374
Adj. R-Sq0.3260.4070.3270.3210.3360.342

Note(s): Standard errors are reported in parentheses. *, ** and *** indicate significance at the 90%, 95% and 99% level, respectively. We conducted several diagnostic checks to assess the assumptions of Model 2. Residual plots confirmed the assumption of homoscedasticity. A histogram of residuals suggested approximate normality. Cook’s Distance revealed one outlier (Cook’s Distance = 0.74), the exclusion of which leave all findings and inferences qualitatively unchanged. No other data point exceeded the critical threshold of 0.5 (mean = 0.016). Multicollinearity was evaluated using the Variance Inflation Factor (VIF), with all predictor variables showing VIF values below 5 (VIFmax = 3.6)

Source(s): Authors’ own work

or Create an Account

Close Modal
Close Modal