Case Study
This project involves two tasks:
a statistical analysis (50%) and written report (50%). You are expected to use Excel to analyse the data and Word (all) to write your report. The final submission should contain two files. An Excel spreadsheet with the data, graphs and analyses, and a Word document (or pdf) of your written report.
Instructions
Attempt question 1 & 2 and explain your answers clearly. Compile a Microsoft Word report of approximately 1000 words and submit your report and excel file.
In this case study, we are analyzing data about 32 Scottish council areas from The Scottish Government online open access source [The Scottish Government, 2018].
Your report must answer the following questions, but you should start with a brief introduction and methods section, and finish with a conclusion summarizing your main findings.
Questions:
For Q1, you need to run two t-tests and create two box plots.
For the second question, you will have to create a scatterplot and run a correlation coefficient.
In total you should have 3 t.tests 3 box plots and 2 correlations 2 scatter plots
Question 1:
Compare and contrast the education and salary statistics of males and females across the different Scottish council areas.
Is the school attainment of males and females across the council areas statistically different?
Are the weekly salaries of males and females across the council areas statistically different?
To answer these questions, you may wish to plot and investigate the following:
Boxplots to compare male and female school attainment, identifying outliers.
A suitable hypothesis test to compare male and female school attainment.
Boxplots to compare male and female weekly salaries.
A suitable hypothesis test to compare male and female weekly salary.
Question 2:
Health Statistics
• Smoker. (%) shows the percentage of current smokers.
• Lung.Cancer.Cases shows the number of lung cancer cases (including cancer of the trachea and bronchus registrations).
This to understand the data each variable is representing.
Investigate the relationship between the health statistics of smoking, lung cancer and life expectancy.
You may wish to consider some of the following:
Are smoking and lung cancer cases correlated?
Are the percentage of smokers correlated with the life expectancy of the area?
