Survival modeling of first birth interval after marriage

Abstract

This is a data exploratory analysis of retrospective cross-sectional study of pattern of first birth interval after marriage in Nigeria. The data for the study are extracted from the published reports of the National Demographic and Health Survey 2009 edition. Fertility as a major component of population change is influenced by first birth interval after marriage, since the interval is positively correlated with the cumulative number of children a woman would have at the end of her reproductive life. Studies have described this interval using non-parametric methods which lack features to project the estimates further. This paper is designed to fill the gap by attempting to fit a parametric model to data on the first birth interval among women of reproductive age in Nigeria. Four parametric models whose various curves and estimates are compared with non-parametric values are considered, namely Inverse Gaussian, Log-logistic, Weibull and Burr Type XII. The best model appears to be Inverse Gaussian based on the Akaike Information Criterion of lowest value of 116617.6. Quantile-quantile plots also identify Inverse Gaussian as model whose data points clustered much around straight line. All other curves give credence to the Inverse Gaussian model as the one that describes the data better than the rest. However, the study does not rule out adaptability of Log-logistic distribution to model waiting time to first birth after marriage since it also behaves similarly to Inverse Gaussian distribution.