Comparison of weighted and matched sample sizes under different levels of covariate overlap. IPTW shows a weighted sample size identical to the original cohort. Matching weights and matching are similarly affected by exposure prevalence and poor covariate overlap, indicating shifts in the target population.
Abbreviations: U: Unmatched cohort, M: Matched cohort; Mw: matching weight cohort; Ip: Inverse probability of treatment weight cohort; pExpo: Exposure prevalence