Predictive accuracy of the logit model to determine factors affecting delivery and postnatal care services utilization in Tanzania

Abstract

Purpose This paper examines factors affecting the delivery care (DC) and postnatal care (PNC) services utilization in Tanzania using the predictive accuracy of the binary logit model by including DC as among the predictors of PNC utilization. Design/methodology/approach The study used secondary data from the Tanzania Demographic and Health Survey and Malaria Indicator Survey (2022) based on a sample of 13,266 women aged 15–49. Binary logit was used to analyze the association between independent variables and each binary dependent variable, followed by a stepwise likelihood ratio test for binary logistic regression analysis to select the most important predictors associated with DC and PNC. Odds ratios were used to predict the likelihood of the occurrence of significant explanatory variables in explaining the outcomes. Findings The results showed that the type of place of residence, wealth index, region, highest educational level, husband/partner’s level of education and respondent’s occupation were significant predictors of DC utilization. In contrast, the woman’s age, region, highest educational level, wealth index, DC and husband/partner’s educational level were significant predictors of PNC utilization. Public health interventions are needed to promote and increase the utilization of delivery and postal care services. The targets should be poor women and those residing in rural or remote areas. Originality/value Including DC as a predictor variable (which was not used before) in PNC utilization improved the predictive power of the model and the robustness of the results.