PROBLEM: A person's systolic blood pressure can be a signal of serious issues in their cardiovascular system. The dataset Blood1.csv???? has the systolic blood pressure, smoking status (coded as 0 = non-smoker; 1 = smoker), and person size (coded as 0 = normal weight; 1 = overweight; and 2 = obese) for 500 randomly chosen adults. The data are from a case study for the 2003 Annual Meeting of the Statistical Society of Canada. In this assignment, you will perform a complete statistical analysis to address if there is a significant difference in mean systolic blood pressure between persons of different sizes.
Do the following in a knitted RMarkdown file.
Do a little data cleaning to create factor versions of the variables that require it.
Discuss if this data is part of a designed experiment or an observational study. How do you know?
Generate a meaningful plot to compare the distributions of the systolic blood pressures between the three size classes. Comment on what you see, including comment on average and variation in evaluation scores.
Run a one-way ANOVA to test to see if there is any difference in true mean systolic blood pressures between the person size classes. You must cite the F-statistic value, both numerator and denominator degrees of freedom, the p-value, and the conclusion in problem context.
Check the model residuals to see if there are any suspected problems among the model assumptions.
Perform appropriate multiple comparisons (only if necessary!) and report the results in context. You must provide a defense of your choice to use Tukey or Dunnett (or neither!)