Estimating nonparticipation bias in a longitudinal study of bereavement

Boyle, Frances M., Najman, Jake M., Vance, John C. and Thearle, M. John (1996) Estimating nonparticipation bias in a longitudinal study of bereavement. Australian and New Zealand Journal of Public Health, 20 5: 483-487. doi:10.1111/j.1467-842X.1996.tb01626.x


Author Boyle, Frances M.
Najman, Jake M.
Vance, John C.
Thearle, M. John
Title Estimating nonparticipation bias in a longitudinal study of bereavement
Journal name Australian and New Zealand Journal of Public Health   Check publisher's open access policy
ISSN 1326-0200
Publication date 1996-10-01
Sub-type Article (original research)
DOI 10.1111/j.1467-842X.1996.tb01626.x
Volume 20
Issue 5
Start page 483
End page 487
Total pages 5
Place of publication Carlton, VIC
Publisher Blackwell Publishing
Language eng
Subject 11 Medical and Health Sciences
Abstract Nonparticipants in epidemiological studies may differ in important respects from participants but the magnitude of this potential bias is rarely quantified. This study estimates the effect of nonparticipation on estimates of mental health problems following stillbirth, neonatal death or sudden infant death syndrome. Of 805 families approached, 512 (64 per cent) were recruited, of whom 77 per cent of mothers and 71 per cent of fathers completed four study interviews. Younger, unmarried, unemployed parents without private health insurance were less often recruited, and even if recruited, were less likely to complete the interview. By evaluating several possible scenarios, we estimated that had mothers lost to follow-up remained in the study, anxiety rates would have varied by no more than ε4 per cent. Relative risks associated with bereaved-control comparisons would have differed little from the observed estimate of 2.33. Estimating the effects of initial nonresponse is more difficult but the adoption of a worst-case scenario produced a relative risk of 3.47. Despite systematic nonparticipation suggestive of social disadvantage, attrition-related bias may have had only a modest effect on anxiety and depression rate estimates. However, this may not be the case when sample loss is high, when associations between attrition and outcome are strong, and when attrition-related behaviour differs across comparison groups.
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Unknown

Document type: Journal Article
Sub-type: Article (original research)
Collection: School of Public Health Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 5 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Fri, 29 Aug 2008, 02:33:05 EST