Estimating the safety impacts in before–after studies using the Naïve Adjustment Method

摘要: ABSTRACTThe before–after study is the most popular approach for estimating safety impacts of an intervention or treatment. Recent research, however, has shown that common approaches can still provide a biased estimate when entry criterion used and characteristics treatment control groups are dissimilar. Recently, new simple method, referred to as Naive Adjustment Method (NAM), been proposed mitigate limitations identified above. Unfortunately, effectiveness NAM using ‘real’ data not yet properly investigated. Hence, this paper examined accuracy group contains sites have different mean values. Simulated two observed datasets were used. The results show outperforms Naive, Control Group, empirical Bayesian methods. Furthermore, it be simpler alternative adjusting estimators documented in previous studies.