Open AccessMonitoring the newly infected cases of COVID-19 data weekly: A Survival Data Analysis (SDA) perspective
Author(s) -
Ramachandran Ramasamy,
Maniam Kaliannan
Publication year - 2021
Publication title -
statistical journal of the iaos
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.286
H-Index - 16
eISSN - 1875-9254
pISSN - 1874-7655
DOI - 10.3233/sji-210804
Subject(s) - weibull distribution , covid-19 , hazard ratio , hazard , survival analysis , scale (ratio) , statistics , term (time) , duration (music) , proportional hazards model , cumulative distribution function , medicine , econometrics , mathematics , geography , cartography , virology , probability density function , outbreak , physics , confidence interval , biology , disease , quantum mechanics , acoustics , infectious disease (medical specialty) , ecology
This paper attempts to fit the best survival model distribution for the Malaysian COVID-19 new infections experience of Wave I/II and Wave III using the well-known Survival Data Analysis (SDA) procedures. The purpose of fitting such models is to reduce the complexity and frequency of the COVID-19 new infections data into a single measure of scale and shape parameters to enable monitoring of weekly trends, undertake short term forecasts and estimate duration when the virality will be contained. The analysis showed a Weibull distribution is the best statistical fit for Malaysia’s new infections COVID-19 data. The estimates of scale and shape parameters for Wave I/II was 0.05901 and 2.48956 and for Wave III was 0.06463 and 2.5693, respectively. Much higher hazard force in Wave III is due to weaker control in the implementation of cordon sanitaire measures imposed in containing the virality spread. Based on the survival function the short-term forecasts showed that the number of new infections projected to decline from 23,282 cases in 28th week to 22,017 cases in 31st week. Similarly, based on the cumulative hazard function the duration estimated for containing the virality completely projected to stretch over another 19.6 weeks under the prevailing conditions.