Final Statistics Project - A Statistical Case Study
For this project, each student MUST complete this project to receive a passing grade for the 4th term. NO EXCEPTIONS!
The goal of this project is to create a statistical case study. This case study must include real world data, a picture, a description of the data, and statistical questions that pertain to the data. In addition, a webpage must be made to host your case study and corresponding data. An additional benefit of having your case study and data on a webpage is that your data, with the help of Rweb, will be able to be analyzed in Rweb.
This project must include the following: 1. REAL Data: This data may be from: a) A scientific website - feel free to investigate the sites found here. b) your own survey c) collected from another class ( as part a physics experiment, for example), d) from another website (polling, etc.)
2. Once you have a data set of interest, please ask me (Mr. Simoneau) to review the data before proceeding. Understand that you must submit/create statistical questions that pertain to your data set. So think about what statistical questions you may be able to ask while choosing which data you would like to use.
3. Once you have a data set, I can start by creating a custom webpage for your project on the STATS4STEM website. Please click on the following link to request a webpage and to gain access. Once the page has been created, an email will be sent to your inbox giving you access. If you didn't receive the invitation, please check your spam folder for the invitation, it may have been sent there.
4. Once you have your data, you must eventually upload your data onto into RStudio. a) Inspect your data to see that there are no missing rows or numbers.
b) VERY IMPORTANT: For column names - Make sure that there are no spaces and that ALL letters are lower case. Replace splaces with periods if you wish. For example:
Change Heat (Celcius) .... simply to .... heat Change Ford Focus .... simply to .... ford.focus
This is important for both Column headers and for any words found in your data.
c) Make sure no column header is no more than 10 characters including periods.
d) Try not to reference the units in the column headers. There needs to be a section on your webpage that displays all the column names / units / and short description.
5. All material must be referenced! I want you to use the following reference guide for referencing. I find it the easiest to use. Each project must have referenced materials. For example, make sure you reference the website(s) used to collect or access your data.
PART B - UPLOAD DATA - INSTRUCTIONS TO UPLOAD DATA FROM GOOGLE DOCS INTO RSTUDIO: 1. Once your data is all set, make sure you don't have any commas or % or $ signs in your data. Also make sure your text (variable names and colleges) is properly formatted with NO spaces or symbols (% bad). Also, make sure you are not missing any data! Make best guess estimate for data you are missing. 2. In google docs, click file, then download as , the choose comma seperated csv file. 3. Once you save the file go to RStudio. Then click "Files" (Files can be found not on the top right, but in the window where you get plots and R help documentation), then "Upload" and then upload your .csv file. 4. Once the data has been uploaded to RStudio, in the command line type: d=read.csv("yourfilenamehere.csv") ### make sure to copy your file name exactly attach(d); names(d) ## the names will give you all the names of your variables
PART C - DATA ANALYSIS
6. 10 Statistical questions must be asked for each problem set. Work to draw questions from all facets of statistics. These questions must be place at the bottom of the webpage.
7. Finally, for each question, provide the correct answer directly below each question.
8. For each case study, a photo must be found that represents the data set. Use a picture from the actual website used to find the data, or find a photo to using the site below. Make sure to check the copyright requirements. Place a citation for the photo in the citations section if required.