To reanalyze the between-population variance in height, weight, and body mass index (BMI), and to provide a globally applicable technique for generating synthetic growth reference charts.
Using a baseline set of 196 female and 197 male growth studies published since 1831, common factors of height, weight, and BMI are extracted via Principal Components separately for height, weight, and BMI. Combining information from single growth studies and the common factors using in principle a Bayesian rationale allows for provision of completed reference charts.
The suggested approach can be used for generating synthetic growth reference charts with LMS values for height, weight, and BMI, from birth to maturity, from any limited set of height and weight measurements of a given population.
Generating synthetic growth reference charts by incorporating information from a large set of reference growth studies seems suitable for populations with no autochthonous references at hand yet.
Large-scale surveys typically exhibit data structures characterized by rich mutual dependencies between surveyed variables and individual-specific skip patterns. Despite high efforts in fieldwork and questionnaire design, missing values inevitably occur. One approach for handling missing values is to provide multiply imputed data sets, thus enhancing the analytical potential of the surveyed data. To preserve possible nonlinear relationships among variables and incorporate skip patterns that make the full conditional distributions individual specific, we adapt a full conditional multiple imputation approach based on sequential classification and regression trees. Individual-specific skip patterns and constraints are handled within imputation in a way ensuring the consistency of the sequence of full conditional distributions. The suggested approach is illustrated in the context of income imputation in the adult cohort of the National Educational Panel Study.