Skip to main content

Table 3 Associations between suicidal ideation with sleep duration at the 2007 survey, the Millennium Cohort Study, n = 63,028

From: Multiple imputation validation study: addressing unmeasured survey data in a longitudinal design

  Average hours of sleep (ref: 7–9)a
≤5
AORb (95% CI) 		6
AORb (95% CI) 		≥10
AORb (95% CI)
Self-reported 5.44 (4.87, 6.07) 2.08 (1.85, 2.33) 6.19 (5.13, 7.46)
PHQ-BIN 5.45 (4.65, 6.38) 2.04 (1.74, 2.39) 5.35 (4.12, 6.93)
PHQ-ORD 6.97 (6.30, 7.71)c 2.20 (1.98, 2.44) 7.45 (6.32, 8.79)
ALL-BIN 5.29 (4.51, 6.21) 1.99 (1.70, 2.33) 6.04 (4.75, 7.69)
ALL-ORD 7.16 (6.47, 7.93)c 2.20 (1.97, 2.45) 7.83 (6.65, 9.23)
  1. aSleep groups based on National Sleep Foundation recommendations [26]
  2. bAdjusted for sex, age, race/ethnicity, marital status, and education
  3. cConfidence interval did not overlap with the 95% CI for the AOR observed for the self-reported suicidal ideation with sleep duration
  4. AOR, adjusted odds ratio; CI, confidence interval; PCL-C, PTSD Checklist−Civilian Version; PHQ, Patient Health Questionnaire; PTSD, posttraumatic stress disorder
  5. Self-reported suicidal ideation was indicated if reported “several days” or more to “thoughts that you would be better off dead or hurting yourself in some way”
  6. PHQ-BIN model: treated suicidal ideation as a dichotomous variable and included the remaining 8 PHQ items in the imputation model
  7. PHQ-ORD model: treated suicidal ideation as a 4-level variable and included the remaining 8 PHQ items in the imputation model
  8. ALL-BIN model: treated suicidal ideation as a dichotomous variable and included the 8 PHQ items and previously identified factors from the literature: sex, age, race/ethnicity, marital status, education attainment, 10 individual items from the RAND physical functioning module, 17 individual items and PTSD screener from the PCL-C, smoking status, sleep duration, and 5 alcohol use items from the PHQ [27,28,29,30]
  9. ALL-ORD model: treated suicidal ideation as a 4-level variable and included the 8 PHQ items and previously identified factors from the literature: sex, age, race/ethnicity, marital status, education attainment, 10 individual items from the RAND physical functioning module, 17 individual items and PTSD screener from the PCL-C, smoking status, sleep duration, and 5 alcohol use items from the PHQ [27,28,29,30]
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us