Comparison of generalized estimating equations and Quasi-Least Squares regression methods in terms of efficiency with a simulation study

• Published in: Communications in statistics. Simulation and computation Vol. 52; no. 3; pp. 1015 - 1025
• Main Authors: Asar, Erdoğan, Karabulut, Erdem
• Format: Journal Article
• Language: English
• Published: Philadelphia Taylor & Francis 04.03.2023; Taylor & Francis Ltd
• Subjects: Convergence; Datasets; Efficiency; Generalized estimating equation; Intervals; Least squares method; Markov correlation structure; Missing data; Quasi-Least Squares regression; Regression; Simulation
• ISSN: 0361-0918; 1532-4141
• DOI: 10.1080/03610918.2021.1872630

Generalized Estimating Equations (GEE) is used to analyze repeated measurements taken from subjects at equal time intervals and is applicable in presence of missing data. In this study, we aimed to introduce Quasi-Least Squares Regression (QLS), which is an extension of GEE and applicable when time intervals are unequal, and compare model performances under different scenarios in terms of efficiency using a comprehensive simulation study. The simulated datasets were analyzed using GEE and QLS, and the results were evaluated. In the simulation study, we produced 9 datasets with 1000 replicates using 3 correlation structures and 3 different correlation values . We obtained 36 scenarios by using 4 working correlation structures on these datasets. According to the results, in general, QLS has superiority over GEE in terms of the efficiency of estimations. In GEE method, a convergence problem was encountered for "Tri-diagonal" working correlation structure. However, in QLS method, there was no problem in convergence for this correlation structure. In order to make better comparisons of GEE and QLS results, Markov working correlation structure should be applicable to GEE as well as QLS. QLS gains an advantage over GEE when repeated measurements are collected at unequal time intervals and there are missing measurements.