Self-controlled case series analyses: Small-sample performance

We derive second-order expressions for the asymptotic bias and variance of the log relative incidence estimator for the self-controlled case series method in a simplified scenario, and study in qualitative terms how bias and variance depend on factors such as the relative incidence and ratio of risk to observation period. Small-sample performance of the estimator in realistic scenarios is investigated using simulations. We find that in scenarios likely to arise in practice, asymptotic methods are valid for numbers of cases in excess of 20

• Type: Journal
• Year: 2008
• Where: CSDA
• Authors: Patrick Musonda, Mounia N. Hocine, Heather J. Whitaker, C. Paddy Farrington
• Keywords: CSDA 2008, Relative Incidence, Relative Incidence Estimator, Self-controlled Case