ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Bayesian Tobit Quantile Regression Modeling In The Case of Length Hospital Stay of COVID-19 Patients

Journal: International Journal of Progressive Sciences and Technologies (IJPSAT) (Vol.33, No. 2)

Publication Date:

Authors : ; ; ;

Page : 178-187

Keywords : Censored Data; Tobit Quantile Regression; Bayesian Tobit Quantile Regression; COVID-19;

Source : Download Find it from : Google Scholarexternal

Abstract

COVID-19 (Coronavirus Disease 2019) is an acute respiratory syndrome infectious disease caused by SARS-CoV-2. The high number of positive cases of COVID-19 in West Sumatra resulted in many patients undergoing isolation and treatment in hospitals. The length of stay of patients varies for each patient because it is triggered by several factors. Data on length of stay for COVID-19 patients is a type of censored data. Therefore, this study aims to model censored data and identify factors that influence the length of stay of COVID-19 patients using the tobit quantile regression method and the Bayesian tobit quantile regression method. This study will also evaluate the goodness of the model using the RMSE and Pseudomodel goodness evaluation methods. The results showed that the Bayesian tobit quantile regression method was a better method in estimating the parameters of the model of length of stay for COVID-19 patients. Meanwhile, it was found that the age of the patient, the diagnosis of the patient in the Positive category and the number of comorbidities had a significant influence on the length of stay of COVID-19 patients.

Last modified: 2022-11-21 02:06:21