Statistical inference in matched case–control studies of recurrent events
Autor: | Grant A. Mackenzie, Chee Fu Yung, Kwok Fai Lam, Jialiang Li, Paul Milligan, Yin Bun Cheung, Xiangmei Ma |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
Male
Epidemiology Computer science Coverage probability Robust statistics Logistic regression 01 natural sciences Cohort Studies 010104 statistics & probability 03 medical and health sciences 0302 clinical medicine Bias Statistics Sampling design Statistical inference Methods Humans AcademicSubjects/MED00860 Computer Simulation 030212 general & internal medicine Point estimation incidence density sampling 0101 mathematics Concurrent design matched case–control study logistic regression Infant Newborn Infant General Medicine Confidence interval Standard error Logistic Models Case-Control Studies Child Preschool Data Interpretation Statistical Female |
Zdroj: | International Journal of Epidemiology |
ISSN: | 1464-3685 0300-5771 |
Popis: | Background 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. Methods 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. Results 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. Conclusions The proposed method is suitable for the analysis of case–control studies with recurrent events. |
Databáze: | OpenAIRE |
Externí odkaz: |