Survival and Multinomial Logistic Regression Analyses of Sekondi-Takoradi District Level National Health Insurance Data in Ghana

摘要

The study applies multinomial regression and survival analysis to a district level health insurance data in Ghana. The study had six response variables and two independent variables which were nominal. At the end of the five year cohort study, the survival plot qualified pregnant women, informal category, and children below age 5 respectively to have performed better with renewal of National Health Insurance Scheme (NHIS) membership. However, people aged 70 and above, were found to be the worst performing in renewal of membership. Log Rank, Breslow, and Tarone-Ware test statistics consistently showed a statistically significant difference among the six categories. Pregnant women were found to be five (5.400) times significantly more likely to renew their NHIS compared to the reference category. The informal category was found to be seven (7.400) times significantly more likely to renew their NHIS than the reference category. Children aged four and below were found to be two times (2.067) significantly more likely to renew their NHIS than the reference category. Children aged 4 and below who are male are less likely (B = -.101 < 0) to renew their NHIS cards compared to the reference group of females. Again, males and females of informal category are equally likely (B = 0) to renew their NHIS cards. For the informal category, males and females are equally likely (B = 0) to renew their NHIS cards. Male SSNIT contributors compared to females are more likely to renew their NHIS cards. The study recommended for the NHIS authorities to find more proactive ways to make renewal of membership easier.