Modelling fertility levels in Nigeria using Generalized Poisson regression-based approach

The rapid increase in total children ever born without a proportionate growth in the Nigerian economy has been a major concern. The total children ever born, being a count data, requires applying an appropriate regression model. Poisson distribution is the ideal distribution to describe this data, but it is deficient due to equality of variance and mean. This deficiency results in under/over-dispersion and the estimation of standard errors will be biased rendering the test statistics incorrect. This study aimed to model count data with the application of total children ever born using a Negative Binomial and Generalized Poisson regression. The Nigeria Demographic and Health Survey 2013 data of women within the age of 15-49 years were used. A comparison of the three models revealed that Generalized Poisson regression is the appropriate model to correct for under/over-dispersion with age of household head (P < .0001), age of respondent at the time of first birth (P < .0001), urban-rural status (P < .0001), and religion (P < .0001) being significantly associated with total children ever born. Early marriage, religious belief and uninformed nature of women who dwell in rural areas should be checked to control fertility levels in Nigeria. (C) 2020 The Author(s). Published by Elsevier B.V. on behalf of African Institute of Mathematical Sciences / Next Einstein Initiative.