A simple random sample of 5000 U.S.-based flights from September 2019 was taken from the Bureau of Transportation Statistics. Here is a link to the sample data: Sample Dataset Link (Sample Dataset Link). The information given can be useful in analyzing on-time performance of different airlines and airports. The goal of this project is to use the data to ask relevant questions and apply our statistical tools to answer these questions. Section I: Understanding the Data For any statistical problem, it is key that we understand the context and type of data that are available. In Section I, you will show your ability to do this. Open the dataset of the random sample in StatCrunch: Sample Dataset Link (Links to an external site.). (You can download or copy/paste this dataset into another statistical program, if you choose.) Open this information page about what each variable represents: Desсrіption of Variables (Links to an external site.) For each column given on in the sample dataset, determine if the variable is Categorical or Quantitative. Note: Many of the data provided in the columns look like numbers, but numbers are often used to identify a label. Use the Desсrіption of Variables that are provided to help you understand the data that has been provided on StatCrunch. On your report, list each variable label, and state whether it is categorical or quantitative. Section II: What is Statistics for? Throughout most of the course, questions have been posed to you, and it was your job to use Statistics to answer the question. For this project, there is a new twist to the problem. I have provided you with the dataset we will be analyzing, it is your job to do TWO things: think of questions that might be asked, then determine an appropriate statistical method for doing so. Using this dataset, I want you to write three different questions to explore. You get to choose the variables to explore and groups to explore from the dataset, each question should focus on these requirements. Question 1: Estimate a parameter (mean or proportion) for any of the variables. Question 2: See if a linear relationship exists between two quantitative variables. Question 3: Choose two groups to compare (e.g. two airlines, two origin airports, etc.), and discern a difference in a proportion or mean of one of the variables. For each of your questions written, identify an appropriate statistical method that you can use to explore your question. On your report, write your three questions, and state the statistical method that you are using the explore your question. Section III: A Picture is Worth 1000 Words Aside from the formal statistical methods that you performed, we can use visual graphs and displays to help support and communicate the same conclusions.
