228k views
2 votes
Suppose that each observation in a random sample of 100 fatal bicycle accidents in 2015 was classified according to the day of the week on which the accident occurred. Data consistent with information on the Insurance Institute for Highway Safety are given in the following table.

Day of the Week Frequency
Sunday 16
Monday 12
Tuesday 12
Wednesday 13
Thursday 14
Friday 15
Saturday 18
a. Based on these data, is it reasonable to conclude that the proportion of fatal bicycle accidents in 2015 was not the same for all days of the week? Use a significance level of 0.05.
b. Write interpretation

User Ajay Ohri
by
3.9k points

1 Answer

2 votes

Answer:

The calculated χ² = 0.57 does not fall in the critical region χ² ≥ 12.59 so we fail to reject the null hypothesis and conclude the proportion of fatal bicycle accidents in 2015 was the same for all days of the week.

Explanation:

1) We set up our null and alternative hypothesis as

H0: proportion of fatal bicycle accidents in 2015 was the same for all days of the week

against the claim

Ha: proportion of fatal bicycle accidents in 2015 was not the same for all days of the week

2) the significance level alpha is set at 0.05

3) the test statistic under H0 is

χ²= ∑ (ni - npi)²/ npi

which has an approximate chi square distribution with ( n-1)=7-1= 6 d.f

4) The critical region is χ² ≥ χ² (0.05)6 = 12.59

5) Calculations:

χ²= ∑ (16- 14.28)²/14.28 + (12- 14.28)²/14.28 + (12- 14.28)²/14.28 + (13- 14.28)²/14.28 + (14- 14.28)²/14.28 + (15- 14.28)²/14.28 + (18- 14.28)²/14.28

χ²= 1/14.28 [ 2.938+ 5.1984 +5.1984+1.6384+0.0784 +1.6384+13.84]

χ²= 1/14.28[8.1364]

χ²= 0.569= 0.57

6) Conclusion:

The calculated χ² = 0.57 does not fall in the critical region χ² ≥ 12.59 so we fail to reject the null hypothesis and conclude the proportion of fatal bicycle accidents in 2015 was the same for all days of the week.

b. It is reasonable to conclude that the proportion of fatal bicycle accidents in 2015 was the same for all days of the week

User Yavindra
by
3.5k points