1 Background The story that was running in the background was about the CAFE, or Corporate Average Fuel Economy standards. In the 1960-70s, collusion among oil-producing countries caused the crude oil price to rapidly increase. In reaction to this, the congress first passed the CAFE regulations in 1975, demanding car producers to raise fuel efficiency to certain standards, within the next 10 years (that is, by 1985). Of course, this pushes research and development (R&D) towards greener cars. What also happened is that for manufacturers who sells a lot in the US, this regulation matters much and the R&D efforts can be seen on other markets. For manufacturers who are not selling a lot in the US, the effect is less clear. Our assignment tries to look at what happened to Volkswagen and Nissans average fuel efficiency during the period 1970-1999, in the EU market. Note that both firms are non-US manufacturers but Volkswagen was selling more in the US, so are supposedly affected by this regulation more than Nissan. But there are also other regulations going on in other markets, at that time.

# ===== Question 2: summarize fuel efficiency by year and manufacturer ===== # Take average of fuel efficiency $mpg for given the firm ($frm) and year ($ye) # You could use the function aggregate() # Then, plot the average $mpg for firm ($frm) Volkswagen ("VW") across all years. # Set your axis label to "year" and "mile per gallon" and put up a title # "Volkswagen fuel efficiency"

# ===== Question 3: merge with gasoline price data ===== # 1) Merge the average fuel efficiency data with crude oil price data, # 2) Create the same plot as above (also for VW) but add a plot of crude oil price over time # when doing so: a) set xlab and ylab to "" in order to not generate any label, # b) generate an axis on the right by using axis(side = 4, ...) # 3) 1985 was the start of the new US regulation on fuel efficiency (which was announced in 1975). # Add a vertical line in the year 1985 to indicate this (search help lty or col for line type or # color; adjust them so that the graph does not look that busy)

# ===== Question 4: find new cars models ===== # Start with the subsetted data focusing on Volkswagen and on "standard" or "intermediate" # or "luxury" cars. # 1) Find the first year where a specific car model (indicated by variable $type) # has positive sales in a given market ($ma); i.e. that's the year when the model started to sell at all # Think of this as the year of introduction; consider using aggregate() # Note: You might want to construct a data frame for this, but in the end merge it with # to the data frame df and assign the merge result to df.augment # 2) Generate a sub-data frame where each car model just started selling for the first/second year; # that is, year <= year of introduction + 1; assign the data frame df.new # 3) Generate average $mpg by year, for all the cars (in our subset) that started selling for the first/second year; # use aggregate() # 4) [Optional] Generate the same plot as in Question 3, but now focusing on the "new cars" that we defined above.