As these previous studies had crossover designs, they included subjects who were dosed on more than one occasion and multiple pharmacokinetic (PK) parameter estimates could therefore be derived for each subject.
In order to assess the influence of missing data, we examined the multiple logistic regression parameter estimates using a complete case analysis, interpolating missing values, and substituting average values.
It contributes to our understanding of how closely spaced objects can be while still being resolvable as separate, in the case where multiple parameters are estimated.
25– 27 If MAR holds, it has been shown that multiple imputation produces unbiased parameter estimates which reflect the uncertainty associated with estimating missing data.
Under the MAR assumption, the maximum likelihood approach and multiple imputation will yield sensible parameter estimates.
Where multiple models are being considered, parameter estimates reported below are from the weighted average of all models under consideration, using R package 'AICcmodavg'AICcmodavg
While multiple imputation methods produce unbiased parameter estimates when the missingness is MAR, this is not the case with complete case analysis.
Finally, uncertainty exists in assigning responsible injections for patients with multiple procedures and in the parameter estimates in our Poisson modeling.
In contrast with list-wise deletion or multiple imputations, FIML yields unbiased parameter estimates when data are missing at random and preserves the overall power and efficiency of the analysis (17).
