Hierarchical Regression Modeling of Some Factors Affecting Weight of Child at Birth
Desmond C. Bartholomew
Department of Statistics, Federal University of Technology, Owerri, Imo State, Nigeria.
Oyinebifun E. Biu
Department of Mathematics & Statistics, Faculty of Science, University of Port Harcourt, Nigeria.
Christopher O. Arimie *
Department of Radiology, University of Port Harcourt Teaching Hospital, Port Harcourt, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
According to World Health Organization (WHO), normal weight of baby at term delivery is (2.5 – 4.2) kilograms. Every child’s birth weight below 2.5 kilograms, regardless of gestational age, is regarded as Low birth weight (LBW). WHO estimates that globally, over 20 million LBW babies are born annually and nearly 95.6% of them in developing countries. Half of all perinatal and 1/3rd of all infant deaths occur in babies with LBW. It is therefore, essential to study some of the factors that causes LBW. Hierarchical Multiple Regression analysis was used to study the effects of mother’s weight, age and height above and beyond mother’s education level in predicting the weight of the child at birth. The results showed that mother’s education level explains about 6.1% of the unexplained variations in the weight of the child at birth in block 1 and mother’s age, weight and height explained about 3.9% above and beyond mother’s education level. This implies that all the variables studied affects the baby’s weight at birth but, the mother’s educational level affects the baby’s weight much more. It was concluded that mother’s education level plays a vital role in predicting the weight of the child at birth because it has a causal effect on the use of prenatal care and improves marriage prospects.
Keywords: Hierarchical multiple regression models, hierarchical linear models, low birth weight, unexplained variation, infant deaths.