Estimating Childhood Stunting and Overweight Trends in the European Region from Sparse Longitudinal Data

Background: Monitoring countries' progress toward the achievement of their nutrition targets is an important task, but data sparsity makes monitoring trends challenging. Childhood stunting and overweight data in the European region over the last 30 y have had low coverage and frequency, with most data only covering a portion of the complete age interval of 0-59 mo.

Objectives: We implemented a statistical method to extract useful information on child malnutrition trends from sparse longitudinal data for these indicators.

Methods: Heteroscedastic penalized longitudinal mixed models were used to accommodate data sparsity and predict region-wide, country-level trends over time. We leveraged prevalence estimates stratified by sex and partial age intervals (i.e., intervals that do not cover the complete 0-59 mo), which expanded the available data (for stunting: from 84 sources and 428 prevalence estimates to 99 sources and 1786 estimates), improving the robustness of our analysis.

Results: Results indicated a generally decreasing trend in stunting and a stable, slightly diminishing rate for overweight, with large differences in trends between low- and middle-income countries compared with high-income countries. No differences were found between age groups and between sexes. Cross-validation results indicated that both stunting and overweight models were robust in estimating the indicators for our data (root mean squared error: 0.061 and 0.056; median absolute deviation: 0.045 and 0.042; for stunting and overweight, respectively).

Conclusions: These statistical methods can provide useful and robust information on child malnutrition trends over time, even when data are sparse.