Skip to main content
. 2014 Feb 14;14:71. doi: 10.1186/1472-6963-14-71

Table 5.

Multiple Tobit regression analyses with mean costs in 3-month period in € (year 2008 values) as dependent variable for total costs and by health care sector

 
Predictor variables
Total costs
Inpatient costs
Outpatient costs
Nursing costs
    b (SE) (p-value) a b (SE) (p-value) a b (SE) (p-value) a b (SE) (p-value) a
Predisposing factors
Age (centered)
13.33**
(4.33)
(0.002)
9.51*
(4.34)
(0.028)
3.44*
(1.41)
(0.015)
2.70***
(0.62)
(0.000)
Female gender (ref: male)
21.65
(55.06)
(0.694)
53.46
(55.52)
(0.336)
-12.91
(17.89)
(0.471)
-2.70
(6.58)
(0.682)
Marital status (ref: married)
Single
139.92
(148.79)
(0.347)
208.98
(187.53)
(0.265)
-5.57
(45.92)
(0.903)
30.72
(30.40)
(0.312)
Divorced
103.85
(104.36)
(0.320)
246.97
(139.17)
(0.076)
-23.71
(32.22)
(0.462)
6.68
(15.69)
(0.670)
Widowed
79.49
(74.99)
(0.289)
146.20
(84.96)
(0.085)
-16.02
(23.70)
(0.499)
6.57
(8.98)
(0.465)
Education (ref: ≤ 9 years of schooling)
10-11 years of schooling
-14.95
(69.77)
(0.830)
-46.73
(65.42)
(0.475)
41.26
(23.29)
(0.077)
9.80
(10.64)
(0.357)
≥ 12 years of schooling
-122.42
(76.53)
(0.110)
-160.88**
(62.54)
(0.010)
-26.87
(25.35)
(0.289)
2.40
(10.25)
(0.815)
Body mass indexc
11.37*
(5.37)
(0.034)
1.74
(5.25)
(0.740)
5.88**
(1.75)
(0.001)
0.54
(0.59)
(0.362)
Enabling
Incomeb c
0.02
(0.043)
(0.653)
0.03
(0.04)
(0.505)
0.02
(0.014)
(0.107)
-0.01
(0.01)
(0.382)
Private health insurance (ref: statutory)
146.31
(106.51)
(0.170)
175.79
(130.97)
(0.180)
54.08
(34.31)
(0.115)
0.85
(14.65)
(0.954)
Lubben social network scalec
4.53
(5.17)
(0.381)
5.92
(5.06)
(0.242)
-1.01
(1.68)
(0.548)
0.31
(0.58)
(0.596)
Need
CIRS-G scorec
41.18***
(5.05)
(0.000)
18.23***
(4.77)
(0.000)
17.19***
(1.64)
(0.000)
3.05***
(0.68)
(0.000)
SF-12 Mental component summary (MCS)c
-13.90***
(2.72)
(0.000)
-8.71***
(2.59)
(0.001)
-3.56***
(0.89)
(0.000)
-1.14***
(0.33)
(0.001)
Averaged pseudo R2
 
0.003
0.008
0.004
0.007
Averaged Chi2   158.04 58.52 195.52 139.65

aMultiple Tobit regression with marginal effects for the unconditional expected value E[y] of the dependent variable; bsquare root equivalence scale for 3 months; *p <0 .05; **p < 0.01; ***p < 0.001; SE = standard error; cthe variable was mean centered; N = 3,124 with multiple imputation, imputation steps 100, cycle length 200. The bold data denotes those effects being significant.