THE ROBUST LOGISTIC REGRESSION MODEL ESTIMATION FOR PATIENTS INFECTED WITH COVID-19 VIRUS
Keywords:
Binary Logistic regression, robust, Mallows Type Class method, weighted maximum likelihood methodAbstract
In this paper, Binary Logistic Regression will be used to measure the probability of death due to infection with Covid-19 virus, which suffers from the presence of outliers in its measurements that represent the dependent variable of the patient's status (1 death and 0 no death) and the explanatory variables represented by the patient's age, weight, gender , diabetic ratio , the level of blood pressure, temperature and the proportion of cytokines of the two types IL-6 and IL-8, which are the cells responsible for decreasing the numbers of lymphocytes and their rise, and they have a key role in robust processes, genetic development, platelet count variable in the blood and variable blood oxygen rate. Two methods were used to estimate the Robust Binary logistic regression model, they are the Mallows Type Class method and the weighted maximum likelihood method WMLE using the Matlab language program, and the comparison between the two methods by means of the statistical criterion, mean squares of error, Akaiki criterion, and Bayes Akaiki criterion, to assess the best method in estimating the probability of death from infection with the virus
Downloads
Published
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.