Skip to main content

Table 2 Estimation results of seemingly unrelated regression model (SUR) and ordinary least square (OLS): physical activity

From: Different conceptual constructs for modelling sedentary behaviour and physical activity: the impact on the correlates of behaviour

Explanatory variables Physical activity  
  OLS SUR % difference in SE (SUR vs. OLS)
  Coef. (ME) a SE b Coef. (ME) a SE b  
Age −0.030(−0.470)*** 0.002 −0.030(−1.596)*** 0.002 0.57
Sex      
 Malesc      
 Females −0.253(0.776)*** 0.046 −0.253(0.759)*** 0.046 0.28
Health status      
 Limiting illnessc      
 Non-limiting illness 0.532(1.702)*** 0.073 0.531(1.744)*** 0.073 0.32
 No illness 0.492(1.636)*** 0.065 0.491(1.704)*** 0.065 0.27
Drinking status      
 Almost every dayc      
 Five or six days a week 0.363(1.438)** 0.112 0.363(1.415)** 0.112 0.41
 Three or four days a week 0.106(1.112) 0.090 0.107(1.101) 0.090 0.34
 Once or twice a week 0.076(1.079) 0.077 0.077(1.028) 0.077 0.32
 Once or twice a month −0.013(0.987) 0.089 −0.012(0.920) 0.088 0.39
 Once every couple of      
 months −0.102(0.903) 0.108 −0.101(0.848) 0.108 0.30
 Once or twice a year −0.233(0.792) 0.109 −0.230(0.763) 0.109 0.39
 Not at all in the last 12 months/non-drinkers −0.257(0.773) 0.109 −0.253(0.762) 0.108 0.40
Access to vehicle      
 Noc      
 Yes −0.228(0.796)** 0.068 −0.210 (0.865)** 0.067 1.94
 Constant 4.187*** 0.127 4.172*** 0.125 1.37
 Observations 2268   2268   
  1. aCoefficient (Marginal Effects/Elasticity); bStandard Error; cOmitted category *Exponentiated ME > 1(negative effect), exponentiated ME <1(negative effect); Significance level of 1% (***), 5% (**); Hausman specification test (null hypothesis: difference in coefficients in two models is not systematic): Chi2 (26) = 0.10; p = 1.000.