Modeling the effects of nutritional and socioeconomic factors on the growth and morbidity of Kenyan school children

Abstract

This paper estimates dynamic models for the height, head circumference, weight, and morbidity of approximately 110 Kenyan school children (6-9 years) in a multivariate longitudinal data framework. Dynamic models allow anthropometric dimensions to depend on the respective measurements in the previous period. The system of 4 equations specified for height, head circumference, weight, and morbidity incorporates the inter-relationships among these variables; explanatory variables in the model consist of nutritional, socioeconomic, demographic, and environmental factors. The model parameters are estimated using the principle of maximum-likelihood, while controlling for the unobserved between-children differences. The main findings are, first, that calcium intakes are positively associated with height while protein and energy intakes are associated with weight. Vitamin A intakes are negatively associated with morbidity. Second, socioeconomic status plus the cash income of the household is a significant predictor of height, head circumference, and morbidity. Third, maternal height is positively associated with children's height and maternal body mass index (BMI) is positively associated with children's weight. Fourth, parents' scores on psychological tests, mother's age, and children's hemoglobin concentration are negatively associated with morbidity while mothers' morbidity is positively associated with children's morbidity. Implications of the modeling results are discussed. Am. J. Hum. Biol. 11:317-326, 1999. Copyright 1999 Wiley-Liss, Inc.