In: Statistics and Probability
An automotive researcher wanted to estimate the difference in distance required to come to a complete stop while traveling 40 miles per hour on wet versus dry pavement. Because car type plays a role, the researcher used eight different cars with the same driver and tires. The breaking distance (in feet) on both wet and dry pavement is shown in the data below. Car 1 2 3 4 5 6 7 8 Wet 107 101 109 112 105 106 111 108 Dry 72 69 74 73 76 75 78 81 a) Construct a 99% Confidence Interval for the mean difference in stopping distance between wet and dry roads. b) Test whether there is a difference in stopping distances between wet and dry roads at 1% level of significance.
(a)
From the given data, values of difference = d = Wet - Dry is got as follows:
Car | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
Wet | 107 | 101 | 109 | 112 | 105 | 106 | 111 | 108 |
Dry | 72 | 69 | 74 | 73 | 76 | 75 | 78 | 81 |
d = Wet - Dry | 35 | 32 | 35 | 39 | 29 | 31 | 33 | 27 |
From the d values, the following statistics are calculated:
n = 8
= 32.625
sd = 3.7773
SE = sd/
= 3.7773/ = 1.3355
= 0.01
ndf =n - 1 = 8 - 1 = 7
From Table, critical values of t = 3.4995
Confidence interval:
32.625 (3.4995 X 1.3355)
= 32.625 4.6735
= ( 27.9515 ,37.2985)
Confidence interval:
27.9515 < < 37.2985
(b)
Test statistic is given by:
t = 32.625/1.3355 = 24.4291
Since the calculated value of t = 24.4291 is greater than critical value of t = 3.4995, the difference is significant. Reject null hypothesis.
Conclusion:
The data support the claim that there is significant difference in stopping distances between wet and dry roads.