Application of generalized estimating equation (GEE) model on students' academic performance

Abstract

This paper illustrates analysis of longitudinal data on students' academic performance using GEE (Generalize Estimation Equations) under various working correlation assumptions. Many factors account for students' academic performance in the fulcrum of all levels of education. Hence, any variable that triggers the academic performance of students evoke the awareness of all. The aim of this thesis is to analyze academic performance using application of Generalized Estimating Equation (GEE) Models under various working correlation assumptions. There are various statistical and mathematical models employed in the analyses of students' academic performance in different level of schools. In this paper, we formulate the Generalized Estimating Equation (GEE) model approach under various correlation assumptions to analyze the probable 3360 Isaac Owusu-Darko et al. performance in relation to variables such as gender, entry age into the school, the geographical location of students, as well as Graded level of former School attended. We used real data set of students' Semester Weighted Average (SWA), and back these with validate and reliable questionnaire about students personal information (on their Biodata response) for a complete data set. From our analyses, the test of model-based and empirical-based standard error estimates on Coefficient Estimation of the Study Parameters based on our GEE assumptions reveals that, only the geographical location of students is significant and hence affects their academic performance. Our contrast effect of linear time interactions with respect to the locations made us recommend an enhancement of mathematics teaching in locations that are lagging, especially in the Northern Belt of Ghana.

The effect of input modes and number of exposures on the learning of L2 binomials

“…The analyses were carried out with the Statistical Package for the Social Sciences (SPSS) software. The data from the two tasks were analysed using Generalised Estimating Equations (GEEs, see Zeger & Liang, 1986), which is an extension of generalized linear models (Owusu-Darko, Kwasi Adu, & Frempong, 2014). While other types of analyses, including generalised linear mixed models (GLMMs), could arguably have been used, GEEs provided the best means of examining the data, as they can be used for a repeated-measures design and accommodate a wide range of different data types (continuous, categorical, etc.…”

Breathing exercise combined with cognitive behavioural intervention improves sleep quality and heart rate variability in major depression

“…The strength of GEE model is that it models a known function of the marginal expectation of the dependent variable as a linear function of explanatory variables (Owusu‐Darko et al . ). GEEs use the GLM to estimate more efficient and unbiased regression parameters relative to ordinary least squares regression in part because they permit specification of a working correlation matrix that can handle missing data and accounts for the form of within‐subject correlation of responses on dependent variables of many different distributions, including normal, binomial and Poisson (Ballinger ).…”

A Proactive Mobile Health Application Program for Promoting Self-Care Health Management among Older Adults in the Community: Study Protocol of a Three-Arm Randomized Controlled Trial

“…In this study, the generalized estimating equation will be adopted to determine the changes or differences between the mHealth + I group, the mHealth group, and the control group (between-group effects), the within-group (time) effects, and the interaction effects (group × time). Since there are 3 time points in this study, the exchangeable working correlation matrix will be used to highlight the same spacing between repeated measurements for each subject [29]. Intention-to-treat will be used as the primary analysis in this study.…”