Using the airline safety dataset spreadsheet, conduct the following operations:
From the spreadsheet, use Excel descriptive statistics to obtain an overall “big picture” view of the data (refer to the readings and resources in this module to identify how to perform this task in Excel).
What are some observations you make from the data? What can you say about the normality or lack of it among the data columns?
Create a histogram of incidents, fatal accidents, and fatalities from the associated columns. What observations can you make from the data?
Create a Pareto chart using airlines and fatal incidents. What does the data suggest?
Take two random samples (at least 50) of the fatalities column. Use the Excel RAND or RANDBETWEEN functions to collect one of your samples. For the second sample, use a method of your choice–including the Sampling function located in the Excel Data Analysis Add-in. Plot the samples. Describe the shape of the resulting sample and comment on its shape with respect to the normal curve. Also, explain any differences in results due to sampling differences.
Examine the contents of each column that includes numbers. Identify which numbers are categorical and which are numeric. Explain your rationale.
What is the probability of three or more fatal accidents occurring during 85-99 for the Airlines on the list? What is the probability of one or more accidents occurring 00-14? Calculate again—and this time remove all airlines from the calculation that had zero incidents.
Note: This is a simple probability estimate assuming nothing more than the mean, the SD, and Z Table values.) Example: approximately 0.28 SD above the mean–per Z table (since this is higher than the mean–and more than the mean is less likely to happen) then: 1- .6103= 0.3897
Your spreadsheet should show your calculations along with a document providing your responses to the questions. In your document, paste charts, graphs, and tables as necessary to aid in explaining the rationale behind your responses.