Skip to main content

Table 3 Fixed effects linear regression model of living arrangement, education/employment, income, and deprivation as exposure variables and average weekly units of alcohol consumption as outcome variable

From: Do changes in social and economic factors lead to changes in drinking behavior in young adults? Findings from three waves of a population based panel study

Model 1: Crude Modelsb 2: Full modelc
Variable β 95% CI β 95% CI
Living arrangement     
Other multiperson household 0.61 -0.72,1.93 0.35 -1.00,1.69
One person household 2.51 1.23,3.79 2.32 1.02,3.63
Couple only or with others -1.23 -2.36,-0.10 -1.37 -2.52,-0.21
Family household (in parent role) -3.56 -5.13,-1.99 -3.84 -5.44,-2.23
Family household (in child role) (ref.) 0   0  
p-value a   < 0.0001   < 0.0001
Education/Employment     
Not in education - employed 0.21 -0.89,1.31 -0.11 -1.36,1.14
Not in education – not employed (NEET) 0.30 -1.10,1.70 0.32 -1.10,1.74
In education - employed 0.16 -0.95,1.28 -0.02 -1.25,1.20
In education -not employed (ref.) 0    
p-value a   0.9772   0.9303
Increase in log personal income 0.36 -0.02,0.74 0.18 -0.27,0.62
p-value a   0.0647   0.4352
One decile increase in area deprivation 0.01 -0.14,0.16 0.02 -0.14,0.18
p-value a   0.9356   0.7747
One unit increase in individual deprivation 0.50 0.14,0.86 0.48 0.10,0.86
p-value a   0.0069   0.0132
  1. aType III Wald tests, which for multichotomous categorical variables (e.g. labour force status) provides a statistical test of the whole construct (not just one non-referent compared to referent comparison).
  2. bThe crude models include each of the independent variables individually.
  3. aThe full model includes all independent variables.