Provide a spreadsheet for the following question:

On page 128 of your text, the authors describe the rollout of the Tesla Model 3 starting in quarter 3 of 2017. The context for the problem was Tesla's desire to make good on the 455,000 pre-reservations for the cars. Another, related, question would be how much experience would it take for the plant to ramp up to reach full capacity, about 1000 cars/day working two 8 hour shifts 300 days of the year.

Table 2 contains a simplified version of the author's data set.

Table 2: Per Unit Production Time for Tesla Model 3 (During Rollout)

Period	Units Produced (X)	Average Days/Unit (Y)
2017-Q3	200	0.325
2017-Q4	2425	0.04952381
2018-Q1	9766	0.015737229
2018-Q2	28578	0.006346262
2018-Q3	53239	0.003449813

First, please graph the data (Ave. Days/Unit versus Units Produced) and then estimate the parameters (Y1 and b) for the learning curve describing Tesla's rollout of the Model 3.

What do you think of the quality of the regression fit? Please speak to R^2, the significance of F for the model, and the significance of the estimates of the slope and intercept, as well as the implications of the residuals.

How many cars would have to be produced before the plant would reach 1000 cars per day? Remember that you were given Y as "days/car" and the inverse of days per car is "cars per day" (which I'm sure Tesla wanted to see at 1000 or more).

Confirm the quality of your fit by graphing the actual Average Days/Unit (Y) against your fitted Average Days/Unit (call it Y-hat). (do you trust the author's data? Or do you think it is too good to be true?)