In: Statistics and Probability
A particular report included the following table classifying 819 fatal bicycle accidents that occurred in a certain year according to the time of day the accident occurred.
Time of Day | Number of Accidents |
---|---|
midnight to 3 a.m. | 47 |
3 a.m. to 6 a.m. | 52 |
6 a.m. to 9 a.m. | 87 |
9 a.m. to noon | 72 |
noon to 3 p.m. | 79 |
3 p.m. to 6 p.m. | 157 |
6 p.m. to 9 p.m. | 191 |
9 p.m. to midnight | 134 |
For purposes of this exercise, assume that these 819 bicycle accidents are a random sample of fatal bicycle accidents. Do these data support the hypothesis that fatal bicycle accidents are not equally likely to occur in each of the 3-hour time periods used to construct the table? Test the relevant hypotheses using a significance level of
α = 0.05.
Let p1, p2, p3, p4, p5, p6, p7, and p8 be the proportions of accidents occurring in the eight different time periods.
State the appropriate null and alternative hypotheses.
H0: p1 =
p2 = p3 =
p4 = p5 =
p6 = p7 =
p8 = 0.08
Ha: H0 is not
true.H0: p1 =
p2 = p3 =
p4 = p5 =
p6 = p7 =
p8 = 0.125
Ha: H0 is not
true. H0:
p1 = p2 =
p3 = p4 =
p5 = p6 =
p7 = p8 = 102.375
Ha: H0 is not
true.H0: p1 =
p2 = p3 =
p4 = p5 =
p6 = p7 =
p8 = 0.8
Ha: H0 is not
true.H0: p1 =
p2 = p3 =
p4 = p5 =
p6 = p7 =
p8 = 819
Ha: H0 is not
true.
Find the test statistic and P-value. (Use technology. Round your test statistic to three decimal places and your P-value to four decimal places.)
X2=
P-value=
State the conclusion in the problem context.
Fail to reject H0. There is convincing evidence to conclude that fatal accidents are not equally likely to occur in each of the eight time periods.
Reject H0. There is not convincing evidence to conclude that fatal accidents are not equally likely to occur in each of the eight time periods.
Fail to reject H0. There is not convincing evidence to conclude that fatal accidents are not equally likely to occur in each of the eight time periods.
Reject H0. There is convincing evidence to conclude that fatal accidents are not equally likely to occur in each of the eight time periods.
Given:
A particular report included the following table classifying 819 fatal bicycle accidents according to time of day the accident occurred.
Time of Day | Number of Accidents |
---|---|
Midnight to 3 a.m. | 47 |
3 a.m. to 6 a.m. | 52 |
6 a.m. to 9 a.m. | 87 |
9 a.m. to Noon | 72 |
Noon to 3 p.m. | 79 |
3 p.m. to 6 p.m. | 157 |
6 p.m. to 9 p.m. | 191 |
9 p.m. to Midnight | 134 |
(a) Let p1, p2, p3, p4, p5, p6, p7, and p8 be the proportions of accidents occurring in the eight different time periods.
The null and alternative hypotheses is
H0: p1 =
p2 = p3 =
p4 = p5 =
p6= p7 =
p8 = 0.125
Ha: H0 is not
true.
Answer - option B
b) Expected frequecy = Total frequency (n) × p
Chi-square goodness of fit test :
Proportion, P | Observed frequency, O | Expected frequency, E | (O-E)^2/E |
1/8 | 47 | 819*1/8 = 102.375 | 29.9525 |
1/8 | 52 | 102.375 | 24.7877 |
1/8 | 87 | 102.375 | 2.3091 |
1/8 | 72 | 102.375 | 9.0121 |
1/8 | 79 | 102.375 | 5.3371 |
1/8 | 157 | 102.375 | 29.1467 |
1/8 | 191 | 102.375 | 76.7218 |
1/8 | 134 | 102.375 | 9.7694 |
n = 819 | 187.037 |
Test statistics:
2 = (O-E)^2/E = 187.037
Degree of freedom, f = k-1 = 8-1 = 7
P-value:
P-value corresponding to 2 = 187.037 with df = 7 is 0.0000
P-value = 0.0000 .....(from chi square table)
Since P-value is less than significance level, = 0.05, we reject null hypothesis.
c) Conclusion:
Reject H0. There is convincing evidence to conclude that fatal accidents are not equally likely to occur in each of the eight time periods.
Answer - option D