Other methods of examining missing data (eg, propensity scores and multiple imputation) will be considered in sensitivity analyses.
The effect of breast feeding on intergenerational social mobility from age 10/11 to age 33/34 was analysed after multiple imputations to fill in missing data and propensity score matching on a wide range of confounders measured in childhood (1958 cohort N=16 039–197054; 1970 cohort N=16 255–16 361).
Thus, other methods of examining missing data, for example, propensity scores, EM algorithm and multiple imputation sensitivity analyses, will be considered.
Presence versus absence of data for each scale will be compared across demographic and clinical characteristics to identify particular groups of individuals that may have a higher propensity for missing data.
Nine patients (1%) could not be assigned a propensity score due to missing data.
As missing data for the variables included in the propensity score affected 1.3% of the study population, we included in the matched analysis only women with a complete dataset.
Particular research interests are the use of modern tools of causal inference, (e..g, propensity score models), problems of missing data, and advanced structural equation models, including mediation analysis.
APACHE II Scores, due to large numbers of missing data, and regional differences were not in the propensity model or core mortality model.
Of the witnessed patients (n=144 074), 3636 (2.5%) had missing timing data; of those otherwise eligible for the analyses (n=100 677), 4598 (4.6%) had contradictory, outlying, or missing data in the variables that were used for propensity score calculation (figure).
Available data will be arranged into quintiles based on this predicted probability (propensity score) and a replacement value for missing data will be selected at random from the available data points within the same quintile.
