Skip to main content

Table 3 Backward logistic regression models for prediction of good sleepers divided by age group, and their performance of prediction

From: Prevalence and impacts of poor sleep on quality of life and associated factors of good sleepers in a sample of older Chinese adults

 

All participants

Age 60-69

Age 70-79

Age 80+

 

(  n = 301)

(  n = 58)

(  n = 135)

(  n = 108)

Constant (Odds ratio)

0.015

0.0002

0.0008

0.029

Dependent variable

Bodily Pain

Vitality

Physical Functioning

Bodily Pain

(Odds ratio, 95% confidence interval)

(1.019** (1.007, 1.032))

(1.051* (1.004, 1.099))

(1.046* (1.000, 1.097))

(1.033** (1.012, 1.054))

 

Vitality

Role-Emotional

Vitality

 
 

(1.025** (1.009, 1.041))

(1..046 (0.995, 1.099))

(1.037* (1.007, 1.067))

 

Classification rate

0.71

0.74

0.73

0.69

Sensitivity

0.51

0.64

0.48

0.54

Specificity

0.77

0.77

0.79

0.74

AUC

0.72###

0.79##

0.77###

0.72##

  1. Variables that show significant association with good sleepers were included in the backward logistic regression model.
  2. The dependent variables were sorted according to ascending level of significance.
  3. AUC: area under the receiver operating characteristic curve (≥0.7: good prediction).
  4. */**/*** significant at the 5%, 1%, and 0.1% level respectively.
  5. #/##/### significantly different from 0.5 at the 5%, 1%, and 0.1% level respectively.
  6. Dependent variable: good sleeper = 1; poor sleeper = 0.