Confounder adjustment in observational comparative effectiveness researches: (2) statistical adjustment approaches for unmeasured confounders / 中华流行病学杂志

ABSTRACT

Observational study of therapy efficacy comparison has been widely conducted to provide the additional efficacy evidence to support randomized control study. Statistical adjustment for unmeasured confounders is a major challenge in observational study of therapy efficacy comparison. This paper summarizes and evaluates the relative statistical methods. Currently, the most commonly used methods include instrumental variable, difference-in-differences (DiD) model and prior event rate ratio (PERR) adjustment. The instrumental variable method skill fully escapes unmeasured confounders through model structure, but it is not easy to obtain satisfied instrumental variables. Both PERR and DiD require the data prior to exposure which are not always collected in observational studies. Unmeasured confounders could result in new requirements and pose new challenges for statistical methods, which needs further study and improvement.