Fig. 2From: Dealing with missing data in laboratory test results used as a baseline covariate: results of multi-hospital cohort studies utilizing a database system contributing to MID-NET® in JapanScenario1 (the risk of diabetes associated with SGA compared to FGA use). Hazard ratios from outcome models with and without baseline blood glucose (SRI, MI, and IPW method were applied by hospital-specific-approach). Abbreviations: aHR, adjusted hazard ratio; CC, complete cases; CI, confidence interval; IPW, inverse probability weighted; MI, multiple imputation; PS, propensity score; SRI, single regression imputation. †The sample size in PS matching with MI gives the mean of 10 matched samplesBack to article page