Statistical approach for analysis of COVID-19: Empirical review

The corona virus disease (COVID 19) was first identified and diagnosed in Wuhan, china in December 2019. It is tremendously communicable which noxiously transmitted to 212 countries and territories throughout the world. It stumbled on India through a student who was all the way from Wuhan on January 30, 2020. By 3rd may 2020 the virus strike more than 37000 people and is currently developing rapidly. It is significant to concenter the number of infections in the whole country. Since our country is consists thickly populated states it’s quite important to analyze the data on the number of infected people across the country. The objective of this paper is to scheme the data of infected people state wise which would help the state government to keep track of the spread and monitor the requirement of health resources accordingly. It would not be appropriate and adequate to analyze with only one model. The analyzation has to be veracious by raising it through other models. Here three growth models namely the logistic, exponential and the susceptible models are established. The data driven model interpreting the results of exponential and logical model exhibits the maximum Daily Infection Rate (DIR) as the outcome. The above mentioned outcome is used to analyze the success of the lockdown. State wise DIR values are interpreted with the results of all the models to categorize the state as less, moderate or highly infected area. It is endowed that Maharashtra, Delhi, Gujarat, Madhya Pradesh, Andhra Pradesh, Uttar Pradesh, and west Bengal or in the highly affected category. Tamilnadu, Rajasthan, Punjab and Bihar are in the moderately affected category. Moreover Kerala, Haryana, Jammu & Kashmir, Karnataka and Telangana are in the controlled category. By establish the various models and interpreting their outcome we tabulate the predicted numbers in state wise manner. A Web application is also constructed to anticipate and fore take the recent updates regularly.