MULTIVARIATE APPROACH TO INVESTIGATE RISK FACTORS PREDISPOSING UNDER-FIVE TO SEVERE BRONCHO-PNEUMONIA

Severe broncho-pneumonia is a leading cause of morbidity and mortality among under-five children worldwide. Identifying risk factors is crucial for targeted interventions. This work applies Principal Component Analysisand Discriminant Analysis to identify therisk factors and predict the prevalence of Broncho-Pneumonia status in under-fivechildren. The data used in this study were collected from health institutions in Minna, Niger state. Predictorvariables which are well-recognized for characterizing broncho-pneumonia were considered, these includes; Weight of Baby at birth,Weightof Baby after a month, Genderof Baby,Age of Mother, Occupation ofMother, Socioeconomic Status, Weather Condition, Nutritional Status, Genetics, Attitudinal Family Background.According to the outcome of other related researchers who conducted comparable studies shows thatthe study predicted the BPn status of new infants using the discriminant model with more than 80% correctly classified. The new datasets were used to validate the model. Researchers also disclosed that baby’s weight at birth is best at discriminating between the two groups, since it has the least value of Wilk’s Lambda compare to other predictor variables.