We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
A study of time trend in global infant mortality rates: Regression with autocorrelated data.
- Authors
Ming Yang; Dejian Lai
- Abstract
Infant mortality rate (IMR) is considered to be one of the most important indices of a country's well-being. Countries around the world and international organizations such as the World Health Organization are dedicating their resources, knowledge and energy to reduce the infant mortality rates (IMR). The well-known Millennium Development Goal 4 (MDG 4), which is an example of such commitment, aims to achieve a two-thirds reduction of the under-five mortality rate between 1990 and 2015. Many statistical tools are developed for data analysis by assuming independence of observations. However, IMR data collected over time forms a time series. The repeated observations of IMR time series are usually not statistically independent. In modeling the trend of IMR, it is necessary to account for these autocorrelations. In this article we proposed to use the general linear models to take into account the autocorrelations to model worldwide IMR. We compared results from general linear model with correlation structure to that from ordinary least squares method to investigate how significantly the estimates change. Our analysis showed that results from these two methods were different for global data but not for specific countries except for two special cases and the discrepancy could be significantly different when considering the population size of the countries. We modeled the trends of IMR from the 1950s to 2010s for selected countries. Our results quantified the trends of IMR over time and measured the difference across countries.
- Publication
International Journal of Child Health & Human Development, 2016, Vol 9, Issue 2, p195
- ISSN
1939-5965
- Publication type
Article