Variation in the CD4 Counts of HIV/AIDS Patients: A Discriminant Analysis Approach

A discriminant analysis is conducted in order to estimate a discriminant function to determine the expected CD4 counts of HIV patients at University teaching hospital in Nigeria. The explanatory variables are CD4 counts, blood group and genotype. Statistically significant differences are observed in the group means of the variables of the two groups HIV-positive& HIV-negative patients. The log determinants are found approximately equal in size for the groups while the Boxs M value shows that the assumption of the equal co-variances is met. Consequently, we proceeded to estimate the discriminant function. The estimated function is significant at 1 per cent level of significance and can explain 54.8 per cent of the variations in the group memberships. The structure matrix shows that the variables CD4 count (0.990), Genotype (-0.205) are very important and the Blood group (0.034) is the least important determinants of the expected status of the patients. Finally, the prediction matrix of the holdout sample shows that 84 per cent of the cases are classified correctly.