Question 1) Suppose you are interested in studying the relationship between the temperature of a particular day and the number of customers that a large ice cream shop serves on that day. To do this you randomly choose 11 days to visit the shop and record both the high temperature of that day and how many customers it served for the entire day. You get the following data: High Temperature (in . F) Number of Customers 75 430 83 480 92 600 77 400 92 510 85 520 73 370 96 590 85 620 88 520 80 430 (a) Draw a scatterplot for this data. Make sure to label your axes. (b) Calculate the correlation coefficient, and decide if there is enough evidence for a correlation. (c) Construct the LSR for this data. Keep one decimal place for the slope and round the intercept to the nearest whole number. (d) Graph the LSR on your scatterplot. (e) Write a sentence interpreting the slope of the LSR. Continued on next page (f) Calculate and interpret the coefficient of determination. (g) How many customers does your model predict will show up on day where the high temperature is 50 F? Would you trust this prediction? (h) How many customers does your model predict will show up on day where the high temperature is 90 F? Would you trust this prediction? (i) Construct the residual plot for this data. Is a linear model appropriate? Why or why not? Extra Credit Question: Suppose that on one of the days in your sample there was an event going on next to the ice cream shop that brought a lot more people to the area. Which of the data points in your sample is most likely from this day? Why? (Hint: The residuals might be useful)