Coronavirus disease 2019(COVID-19) is aninfectious diseasecaused bysevere acute respiratory syndrome coronavirus 2(SARS-CoV-2). As of 1 May 2020,more than 3.25 million caseshave been reported across 187 countries and territories, resulting inmore than 233,000 deaths. More than 1.01 million people have recovered.(Source: Wikipedia)

Looking at the exponential growth in the reported cases. Many countries around the world have declared complete lockdown of the country and bringing the halt to the economy. Among these group of population one school of thought claims that "COVID-19 is just like any other flu".

Assume this to be your Null Hypothesis: There is no difference between the COVID 19 and a 'Normal Flu'

Prepare your Alternate Hypothesis proving that COVID 19 is more dangerous and infectious compared to a normal flu.

Given the above statements following is the expectation from the project: -

Part 1: Collect Your Dataset

You can collect your data from any reliable website.

Current website that I'm following ishttps://www.worldometers.info/. You can also choose a website of your own.

Kaggel or Github has also recently come out with a Covid 19 dataset:https://github.com/datasets/covid-19

Part 2: Exploratory Data Analysis

In this part you are expected to do some exploratory data analysis on the dataset. It basically includes providing summary analysis. Plotting various types of plots and tables showing useful information about your data.

Attaching one example of EDA done on COVID 19.

https://onlinelibrary.wiley.com/doi/full/10.1002/jmv.25743.

Make sure to write with proper analyses and explanation of each plot and table with proper label and axis. Pasting just the diagram with no explanation will not gain you any points.

Minimum number of plots and tables required : 5

Part 3: Hypothesis Testing

(Hint: It will be a one-sided hypothesis of '>' greater than).

You can use any parameter to prove this hypothesis. The most common and powerful parameter would be either the avg number/proportion of deaths or avg number/proportion of cases affected

(Hint: It will be a one-sided hypothesis of '>' greater than because your proving COVID-19 is more dangerous than a normal flu).