Table 4.

Reliability, floor, ceiling effect, and measurement error of the Insomnia Severity Index Danish version (n = 163)

Floor effects, n [%]	11 [4.4]
Ceiling effects, n [%]	0 [0.0]
Reliability
Internal consistency, Cronbach’s alpha [inter-item correlation range]
Global scale (all 7 scale items)	0.90 [0.52–0.80]
Model 2
Severity subscale (item 1, 2, 3, 4)	0.83 [0.74–0.88]
Impact subscale (item 5, 6, 7)	0.88 [0.85–0.92]
Model 4
Severity subscale (item 1, 2, 3)	0.75 [0.38–0.55]
Dissatisfaction subscale (item 1, 4, 7)	0.81 [0.50–.072]
Impact subscale (item 5, 6, 7)	0.88 [0.63–0.79]
Test-retest reliability
ICC [95%CI]	0.90 [0.87–0.93]
Measurement error
SEM ($\sqrt{\mathit{\text{mean}}}\mathit{\text{square}}\left(\mathit{\text{ANOVA}}\right)$)	2.52
SDC (1.96 ×  √ 2 × SEM)	6.99
LoA (mean difference between test and retest) [95% limits]	0.05 [−6.92–7.02]

ICC Intraclass correlation, CI confidence interval, SEM standard error of measurement, SDC smallest detectable change, LoA limits of agreement