#ADVANCED STATISTICS 2020 MIDTERM
#Download your assigned dataset and read the accompanying codebook.
#Which dataset are you working with? Describe your dataset.
#Install and/or load the necessary packages for the commands you use (you can come back and add these as you need them):
#Load your data into R:
#Summarize your data in some way and check that it loaded properly and is what you and the codebook expect:
#Choose two variables from the dataset that you think may have an interesting and potentially causal relationship. Which variables did you choose?
#In at least a paragraph, explain why you chose these variables, what relationship you think they could have, and why you think they have that relationship.
#Describe and visualize each variable separately:
#What did you learn from these descriptive statistics?
#Describe and visualize the two variables together:
#Correlate them:
#Plot them:
#What did you learn from this? How are the variables related (or not)?
#Regress one of the variables on the other.
#1) Which is your independent variable (or x)?
#2) Which is your dependent variable (or y)?
#3) In at least a paragraph, consider the assumptions of OLS and how your data do or do not violate those assumptions.
#4) In at least a paragraph, explain your bivariate regression results. What do your results say? What do your results mean?
#Choose a third variable and run a multivariate regression.
#1) Which variable did you choose and why?
#2) In at least a paragraph, explain your multivariate regression results. What do your results say? What do your results mean? What changed when you added a third variable? What is that third variable doing? Why do you think that change (or no change) happened?
#Finally, in at least a paragraph, discuss how you would change either model if you had more data and time, and why you would make those changes.