Complete vaccination service utilization inequalities among children aged 12-23 months in Ethiopia: a multivariate decomposition analyses

Background Although World Health Organization works to make vaccination service available to everyone everywhere by 2030, majority of the world's children have been unvaccinated and unprotected from vaccine-preventable diseases. In fact, evidences on factors contributing to changes in vaccination coverage across residential areas, wealth categories and over time have not been adequate. Therefore, this study aimed at investigating inequalities in vaccination status of children aged 12-23 months owing to variations in wealth status, residential areas and over time. Methods Maternal and child health service data were extracted from the 2011 and 2016 Ethiopian Demographic and Health Survey datasets. Then, multivariate decomposition analysis was done to identify the major factors contributing to differences in the rate of vaccination utilization across residences and time variations. Similarly, a concentration index and curve were also done to identify the concentration of child vaccination status across wealth categories. Results Among children aged 12-23 months, the prevalence of complete childhood vaccination status increased from 20.7% in rural to 49.2% in urban in 2011 and from 31.7% in rural to 66.8% in urban residences in 2016. The decomposition analyses indicated that 72% in 2011 and 70.5% in 2016 of the overall difference in vaccination status was due to differences in respondent characteristics. Of the changes due to the composition of respondent characteristics, such as antenatal care and place of delivery were the major contributors to the increase in complete childhood vaccination in 2011, while respondent characteristics such as wealth index, place of delivery and media exposure were the major contributors to the increase in 2016. Of the changes due to differences in coefficients, those of low wealth status in 2016 across residences significantly contributed to the differences in complete childhood vaccination. On top of that, from 2011 to 2016, there was a significant increment in complete childhood vaccination status and a 59.8% of the overall increment between the surveys was explained by the difference in composition of respondents. With regard to the change in composition, the differences in composition of ANC visit, wealth status, place of delivery, residence, maternal education and media exposure across the surveys were significant predictors for the increase in complete child vaccination over time. On the other hand, the wealth-related inequalities in the utilization of childhood vaccination status were the pro-rich distribution of health services with a concentration index of CI = 0.2479 (P-value < 0.0001) in 2011 and [CI = 0.1987; P-value < 0.0001] in 2016. Conclusion A significant rural-urban differentials was observed in the probability of a child receiving the required childhood vaccines. Children in urban households were specifically more likely to have completed the required number of vaccines compared to the rural areas in both surveys. The effect of household wealth status on the probability of a child receiving the required number of vaccines are similar in the 2011 and 2016 surveys, and the vaccination status was high in households with high wealth status. The health policies aimed at reducing wealth related inequalities in childhood vaccination in Ethiopia need to adjust focus and increasingly target vulnerable children in rural areas. It is of great value to policy-makers to understand and design a compensation mechanism for the costs incurred by poor households. Special attention should also be given to rural communities through improving their access to the media. The findings highlight the importance of women empowerment, for example, through education to enhance childhood vaccination services in Ethiopia.