Researchers in demography were interested in capturing the relationship between the ethnic make up of neighborhoods and the level of education. To gather data they took a random sample of 100 neighborhoods and recorded the proportion of residents in each that identified as hispanic and the proportion of residents that had graduated from college. The data can be loaded with the following command:
LA <- read.csv("http://andrewpbray.github.io/data/LAed.csv")Plot the relationship between ethnicity and education, keeping in mind the norm of putting the independent variable on the x-axis. Please describe the structure in the plot as well as any unusual observations.
Fit a linear model to this scatterplot. Have you found a predictor that is statistically significant? In your regression output, what do you look for as evidence and how do you interpret it?
Was your inference conclusion based on a valid model? Please use plots to assess the conditions for regression.
To be read next week…
Chapter 6, number 4 (not d), 5, and 6.