1. The data in "StoppingDistance" give the stopping distances y (in feet) after brakes are applied for cars traveling at the indicated speeds x (in miles per hour).
2. Suppose that you want to fit the linear model, y= ₀ + ₁ x+ , to the data.Draw a scatterplot of y versus x. Comment on which model assumption(s) appear to be violated based on the scatterplot.
3. Comment on what is revealed by the residual plot of residuals versus fitted values. Also, do an Anderson-Darling normality test of the residuals making sure to include the p-value.
4. What does a lack-of-fit test say about the linear model we considered in part (a)? Does it support what you see in the scatterplot?
5. Create a new variable equal to the square root of y. [In Minitab, use Calc > Calculator, enter a new variable name (such as sqrty) in the "Store result in variable" box, and in the "Expression" box enter sqrt(y).] Provide a plot of sqrty versus x. Consider the regression model, sqrty= ₀ + ₁ x + . Fit this model and report the fitted equation along with a plot of the residuals versus predicted values.
6. Using the model in part (d), report a 95% prediction interval for stopping distance at a speed of 26 mph? Remember to consider the transformation to y! Interpret this interval in the context of the problem.

y	x
4	4
2	5
8	5
8	5
4	5
6	7
7	7
9	8
8	8
13	8
11	8
5	9
5	9
13	9
8	10
17	10
14	10
11	12
21	12
19	12
18	13
27	13
15	13
14	14
16	14
16	15
19	16
14	16
34	16
29	17
22	17
47	18
29	18
34	18
30	19
48	20
55	21
39	21
42	21
35	22
56	24
33	25
59	25
48	25
56	25
39	26
41	26
78	27
57	27
64	28
84	28
68	29
54	29
60	30
101	30
67	30
77	31
85	35
107	35
79	36
138	39
110	40
134	40