Joint modeling of two count variables using a shared random effect model in the presence of clusters for complex data

Abstract

In epidemiology, it is often the case that two or more correlated count response variables are encountered. Under this scenario, it is more efficient to model the data using a joint model. Besides, if one of these count variables has an excess of zeros (spike at zero) the log link cannot be used in general. The situation is more complicated when the data is grouped into clusters. A Generalized Linear Mixed Model (GLMM) is used to accommodate this cluster covariance. The objective of this research is to develop a new modeling approach that can handle this situation. The method is illustrated on a global data set of Covid 19 patients. The important conclusions are that the new model was successfully implemented both in theory and practice. A plot of the residuals indicated a well-fitting model to the data.

KEYWORDS:

• Joint model
• Generalized Linear Mixed Model
• cluster
• spike at zero
• Covid 19

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Marina Roshini Sooriyarachchi

Marina Roshini Sooriyarachchi, is a senior professor in the Department of Statistics, University of Colombo, Sri Lanka. She obtained her basic degree in Mathematics and Statistics (1985) and Postgraduate Diploma in Applied Statistics (1987) from the University of Colombo. She obtained her MSc in Biometry (1989) and PhD in Applied Statistics (1994) from the University of Reading, UK. She has over 100 research papers in peer-reviewed indexed journals and conferences. She also has over 350 citations to her credit. She has won many research awards at international, national, and local levels. She has one PhD student, one MPhil student, and two students in the pipeline.