Skip to main content

Table 5 Results of the random-effects logit regression model: patient sample (n = 79)

From: Investigating preferences for support with life after stroke: a discrete choice experiment

Attribute

Î’-coefficient

95% CI

P value

MRS (mins)

95% CI

Format of service

       

_One to one

0.7396*

0.6092

1.0814

0.0000

128.61

87.11

175.91

Service provider_hospital

0.1815*

0.5468

0.3752

 

31.56

8.52

57.04

_Community health team

0.0474

-0.1074

0.2268

0.5330

   

_Voluntary organisation

-0.2289*

-0.4282

-0.1037

0.0020

-39.80

-69.89

-16.00

Journey time (minutes)

-0.0058*

-0.0084

-0.0050

0.0000

   

Additional social and leisure

       

_Provided

0.3684*

0.2015

0.6638

0.0000

64.07

30.24

103.43

Constant

-0.2027

-0.4693

0.0270

0.0630

   
  1. No. observations = 653; No. individuals = 79; Wald chi2 (5) = 117.67; Log likelihood = -371.32.
  2. *Statistically significant at P < 0.05.
  3. 95% confidence intervals generated using non-parametric bootstrapping.
  4. Marginal rate of substitution values = β-coefficient for significant attribute/β-coefficient for journey time.
Back to article page

BMC Health Services Research

ISSN: 1472-6963

Contact us