Project on US weather data

Relatório desenvolvido para a disciplina de Estatística Aplicado.

This analysis explores data from the NOAA Storm Database to identify severe weather events that are most harmful to human health and those causing the greatest economic damage. Tornadoes cause the highest fatalities and injuries, while floods result in substantial property damage. The data is cleaned, transformed, and summarized to provide insights into these impacts.

This report analyzes storm data from the U.S. National Oceanic and Atmospheric Administration (NOAA) between 1950 and 2011. It identifies which types of severe weather events have the most significant effects on public health and economic damages. The analysis uses R and includes visualizations for the top 10 events by fatalities, injuries, and property damage.

my work

In this document I demonstrated my expertise in data wrangling and statistical analysis. The first step I carried out data management/manipulation this to ensure that the data is free from errors. Second step I performed Exploratory data analysis in both categorical and continuous variables where in categorical variables I only bar graphs and tabless in form of frequencies and percentages. On the other, I explore continuous variables with differents chart including histogram this check the mean distribution of the continuous variables , box plots to check the outliers and median distribution and again I correlation heatmap to check the correlation between the continuous variables. Thereafter, I performed some regression analysis e.g linear regression, logistics and cox regression as well as hypothesis testing e.g One sample t test and two samples t test . All these is to demonstrate my skills in data science and statistics.