Generalized Estimating Equations (GEE) Approach for Clustered Binary Data with Application to COVID-19 Treatment
Abstract
Clustered binary data frequently occur in epidemiology and other applied fields such as clinical trial studies, where observations within the respective samples are correlated. In such situations, the standard logistic regression method is not valid as logistic regression requires the observations to be independent of one other. This situation arises when treating COVD-19 patients. Patients from certain clusters, such as geographic areas or the same family, are highly correlated, and we need to fit the model using the GEE approach. In this paper, Standard Logistic Regression (LS), Generalized Linear Models (GENMOD), and GEE procedures have been utilized for comparison purposes. Simulated data have been used for case study analysis. The GEE model's accuracy rate is superior when data are binary clustered. For more information about the GEE and GENMOD methods, see Fitzmaurice, Laird, and Ware (2011); Hardin and Hilbe (2003); Diggle et al. (2002); Lipsitz et al. (1994).
Generalized Estimating Equations (GEE) Approach for Clustered Binary Data with Application to COVID-19 Treatment
Volstorff A
Clustered binary data frequently occur in epidemiology and other applied fields such as clinical trial studies, where observations within the respective samples are correlated. In such situations, the standard logistic regression method is not valid as logistic regression requires the observations to be independent of one other. This situation arises when treating COVD-19 patients. Patients from certain clusters, such as geographic areas or the same family, are highly correlated, and we need to fit the model using the GEE approach. In this paper, Standard Logistic Regression (LS), Generalized Linear Models (GENMOD), and GEE procedures have been utilized for comparison purposes. Simulated data have been used for case study analysis. The GEE model's accuracy rate is superior when data are binary clustered. For more information about the GEE and GENMOD methods, see Fitzmaurice, Laird, and Ware (2011); Hardin and Hilbe (2003); Diggle et al. (2002); Lipsitz et al. (1994).