A Statistical Non-Parametric data analysis for COVID-19 incidence data

BACKGROUND: The impact of COVID-19 on the Global scale is tremendously drastic. There are several types of research going on across the world simultaneously to understand and overcome this dire pandemic outbreak. This paper is purely a statistical study on a distinct set of datasets regarding COVID-19 in India. The motivation of this study is to provide an insight into the rapid growth of confirmed COVID-19 cases in India. METHODS: The rapid growth of COVID-19 cases in India started in March 2020. The main objective of this paper is to provide a solid statistical model for the policymaker to handle this kind of pandemic situation in the near future with nonlinear data. In this paper, the data was got from 1st April to 29th November 2020. To come up with a solid statistical model, various nonlinear data such as confirmed COVID-19 cases, maximum temperature, minimum temperature, the total population (state-wise), the total area in km2 (state-wise), and the total rural and urban population count (state-wise) have been analyzed. In this paper, six different Generalized Additive Models (GAM) was identified after a thorough analysis of other researchers’ (Xie and Zhu, 2020; Prata et al., 2020) findings. RESULTS: In all perspectives, the results were identified and analyzed. The GAM model regarding total COVID-19 confirmed cases, total population, and the total rural population provides the best average fit of R2 value of 0.934. As the population value is quite high, the author has concise it using logarithm to provide the best [Formula: see text]-value of 0.000542 and 0.001407 for a relation between the total number of COVID-19 cases regarding the total population and total rural population respectively.