The sensitivity of the results to the imputation of missing data was explored.
Two sets of missing data were explored to determine whether missing data were randomly distributed across study variables.
Sensitivity of the results to imputation of missing data was explored by running the models with and without imputation.
After excluding participants with missing data, we explored the association between categories of exposure and FVC and FEV1, with linear regression using the low exposure category as reference.
However, the impact of missing data was explored for the four families (2.6 %) with partial data (7-month data available but not 13-month), using the last value carried forward.
Finally, a report from the National Research Council NRCC) [ 8], published in 2010, states the necessity of conducting sensitivity analyses using different approaches to deal with missing data to explore the robustness of conclusions to alternative assumptions about the missing data.
Potential implications of missing data will be explored by using multiple imputation techniques.
Patterns of missing data will be explored prior to analysis, and accounted for in the analysis by imputation methods [ 61].
The potential effects of missing data will be explored under various models for nonignorable missing data mechanisms, and through multiple imputation models under ignorable missing data assumptions [ 51].
36 The potential effects of missing data will be explored under various models for nonignorable missing data mechanisms and through multiple imputation models under ignorable missing data assumptions.
