Suppose that we would like to estimate the total number of counties in the us. the uscounties data file contains information on the number of counties in each state, as well as the land area and population (the data file isn't necessary to answer this question.)

sample 1 contains a sample of 30 states randomly selected with probability proportional to the land area of each state (with replacement); sample 2 contains a sample of 30 states randomly selected with probability proportional to the population of each state (with replacement).

(a) which of the above samples (land area or population count) would you expect to provide a better estimate of the total number of counties in the us?