Christian Rudder works for the dating web site Okcupid, and has written a book, Dataclysm, about some surprising data collected from the web site. As an example, here are scatterplots he gives for women and for men. The horizontal axis is the age of the man or woman being interviewed. The vertical axis is the age which they think looks most attractive in the opposite sex. (The data are aggregated, so each point on the plot is actually an average age of people found most attractive for a group of men or women of the same age.) Age Most Attractive in Men Age Most Attractive in Women 40 0000 0000 0 0900 00 20 25 30 35 40 45 50 20 25 40 45 50 Woman's Age Man's Age 1. What variables were measured on each observational unit? (Hint: There are three variables.) Is each variable categorical or quantitative? 2. To what population can we generalize if we use these data for inference? 3. Based on the scatterplots above, guess the value of the correlation coefficient for each data set. 4. Estimate the value of the regression line slope for each data set using the scatterplots above. Hint: For each plot, take a nice range of ages on the x-axis, say from 20 to 40, and approximate how much the line changes from the lower x value to the upper one. The change in y divided by the change in x gives the slope estimate