Question 6 (15 points) A boutique co'ee company serving organic fair trade coffee decides to operate a truck in several areas of Los Angeles. The le coffee-truck. csv is available, where each row corresponds to the sales of the truck on a different day. The following variables are provided: Variable Description price The price of coffee on that day promotion A variable that is 1 if there was a promotion on social media on that day1 0 otherwise weekday A variable that is 1 if this observation corresponds to a weekday (Mon / Tue / Wed [Thu / Fri) , 0 otherwise location The location in which the truck operated on that day (one of: Westwood, Studio City, Silver Lake1 Echo Park and Downtown) sales The number of coffees sold on that day Our goal will be to predict the sales quantity sales. Run a linear regression of sales using all of the variables. You can do this in B. using the following commands: coffee.df = read.csv("coffee-truck.csv") coffee.df$location = as.factor(coffee.df$location) coffee.lm = lm(sales " price + promotion + location + weekday, data = coffee.df} summary (coffee . 1m) Answer the following questions: (a) What fraction of the variation in sales is explained by this model? (1 point) [b] \"Which variables are statistically signicant at the o: = 0.05 signicance level? (3 points) (c) W'hat is the interpretation of the intercept? {2 points) (d) W'hat is the interpretation of the slope of price? {1 point) (e) What is the interpretation of the slope of weekday? (2 points) (f) What is the estimate of the stande deviation 0 of the error term E in the true model? {'2 points) (g) Next Saturday1 the truck will be located in Echo Park and will sell coffee for $5.75, with pro motions planned on social media. Mat is the model's prediction for the number of co'ees sold by the truck? {2 points) [h] For the scenario in (g), nd the 99% prediction interval. (2 points)