Reviewing of Different Methods for Handling Longitudinal Count data

In this paper, we will review the methods that used to handle longitudinal data in the case of marginal models when inferences about the population average are the primary focus [1] or when future applications of the results require the expectation of the response as a function of the current covariates [7]. We will review the generalized estimating equations method (GEE), quadratic inference functions (QIF), generalized quasi likelihood (GQL) and the generalized method of moments (GMM). These methods will be reviewed by discussing its advantages and disadvantages in more details.

Application of Marginal Models to Identify Risk Factors of Childhood Stunting in Ethiopia

Background: Child malnutrition is an underlying cause of almost half (45%) of child deaths, particularly in low socioeconomic communities of developing countries. In Ethiopia, the prevalence of stunting decreased from 47% in 2005 to 39% in 2016. Objective: The main objective of the study was identifying risk factors of stunting among under-five children in Ethiopia using marginal models.Methods: Data was taken from the EDHS 2016, which is a nationally representative survey of children in the 0-59 month age groups. Generalized estimating equation and alternating logistic regression models from marginal models family were used for the analysis. Results: The result of the analysis revealed that the variables child’s age, mother’s education level, mother’s body mass index, place of residence, wealth index and previous birth interval were found to be significant determinants of childhood stunting in Ethiopia and from the result it is revealed that children born with lower previous birth interval (less than 24 months) were more likely to be stunted than those born within higher birth interval. Children of rural Ethiopia were more likely to be stunted than children of urban Ethiopia. Conclusion: It is suggested that for reducing childhood malnutrition, due emphasis should be given in improving the knowledge and practice of parents on appropriate young child feeding practice and frequent growth monitoring together with appropriate and timely interventions.

Analysis of correlated data with feedback for time-dependent covariates in psychiatry research

In studies on psychiatry and neurodegenerative diseases, it is common to have data that are correlated due to the hierarchical structure in data collection or to repeated measures on the subject longitudinally. However, the feedback effect created due to time-dependent covariates in these studies is often overlooked and seldom modelled. This article reviews the methodological development of feedback effects with marginal models for longitudinal data and discusses their implementation.