The results remained unchanged after using two methods of missing data replacement, the maximum bias method, and the mean value of the group.
It might be of interest, however, to compare how sensitive the statistical models are to several methods of missing data imputation such as multiple imputation.
We have performed an extensive simulation study using two clinical data sets and two published predictive models to compare the performance of four methods of missing value imputation for missing data completely at random.
However, we found little difference in the model coefficient estimates for the analyses of the full dataset of 11 212 subjects using CCA and both methods of missing data imputation.
A review of publications from cohort studies with exposures measured in multiple follow-up waves by Karahalios et al. [ 2], points out the continuing use of inappropriate methods of missing data handling and the lack of adherence to the STROBE guidelines.
Wothke has shown that no other missing data handling method, regardless of missing data mechanism, performs better [ 88].
(For ants only) Accept as SSOG only if no evidence could be found that homologous genes were missed in other genomes (see Materials and Methods: Identification of missing gene models).
To check the sensitivity of our method of imputing missing values, we also predicted the missing values by regressing them on other background characteristics.
This method of modeling missing data assumes that the data are missing at random and permits inclusion of all available cases, although it is not as efficient as multiple imputation procedures.
Missing laboratory data is a common issue, but the optimal method of imputation of missing values has not been determined.
A sensitivity analysis using the Last Observation Carried Forward method for handling of missing data was also performed.
