Affordable Access

deepdyve-link
Publisher Website

Statistical inference in matched case-control studies of recurrent events.

Authors
  • Cheung, Yin Bun1, 2, 3
  • Ma, Xiangmei2
  • Lam, K F2, 4
  • Li, Jialiang5
  • Yung, Chee Fu6
  • Milligan, Paul7
  • Mackenzie, Grant8, 9, 10, 11
  • 1 Signature Programme in Health Services & Systems Research, Duke-NUS Medical School, Singapore 169857. , (Singapore)
  • 2 Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore 169856. , (Singapore)
  • 3 Center for Child Health Research, University of Tampere and Tampere University Hospital, Tampere 33520, Finland. , (Finland)
  • 4 Department of Statistics and Actuarial Science, University of Hong Kong, Hong Kong, China. , (China)
  • 5 Department of Statistics and Applied Probability, National University of Singapore, Singapore 117546. , (Singapore)
  • 6 Infectious Disease Service, KK Women's and Children's Hospital, Singapore 229899. , (Singapore)
  • 7 Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London, WC1E 7HT, UK.
  • 8 Medical Research Council Unit The Gambia at London School of Hygiene & Tropical Medicine, PO Box 273, Fajara, The Gambia. , (Gambia)
  • 9 New Vaccines Group, Murdoch Children's Research Institute, Melbourne, Victoria 3052, Australia. , (Australia)
  • 10 Faculty of Infectious and Tropical Diseases, London School of Hygiene & Tropical Medicine, London, WC1E 7HT, UK.
  • 11 Department of Paediatrics, University of Melbourne, Parkville, VIC 3010, Australia. , (Australia)
Type
Published Article
Journal
International Journal of Epidemiology
Publisher
Oxford University Press
Publication Date
Jun 01, 2020
Volume
49
Issue
3
Pages
996–1006
Identifiers
DOI: 10.1093/ije/dyaa012
PMID: 32125376
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

The concurrent sampling design was developed for case-control studies of recurrent events. It involves matching for time. Standard conditional logistic-regression (CLR) analysis ignores the dependence among recurrent events. Existing methods for clustered observations for CLR do not fit the complex data structure arising from the concurrent sampling design. We propose to break the matches, apply unconditional logistic regression with adjustment for time in quintiles and residual time within each quintile, and use a robust standard error for observations clustered within persons. We conducted extensive simulation to evaluate this approach and compared it with methods based on CLR. We analysed data from a study of childhood pneumonia to illustrate the methods. The proposed method and CLR methods gave very similar point estimates of association and showed little bias. The proposed method produced confidence intervals that achieved the target level of coverage probability, whereas the CLR methods did not, except when disease incidence was low. The proposed method is suitable for the analysis of case-control studies with recurrent events. © The Author(s) 2020. Published by Oxford University Press on behalf of the International Epidemiological Association.

Report this publication

Statistics

Seen <100 times