STA3030F Tutorial 2
All questions in this tutorial should be done by hand and handed to your tutor during
Tutorial 3.
Question 1
Personnel consultants are interested in establishing whether there is any difference in the mean age
of the senior managers of two large corporations. The following data gives the ages, to the nearest
year, of a random sample of 10 senior managers, sampled from each corporations:
Mean
Corporation 1 52 50 53 42 57 43 52 44 51 34 47,8
Corporation 2 44 45 39 49 43 49 45 47 42 46 44,9
A bootstrap simulation was performed in which 2000 data sets of size 20 were regenerated from
the original data, and split into two groups of size 10 each. The resultant differences in means
(Corporation 1 - Corporation 2) from the two groups were sorted from smallest to largest. A
summary of the differences observed in the sorted list is given below:
Rank 1 25 75 100 150 500 750 1000 1250 1500 1750 2000
Value -4.3 -3.7 -3.2 -2.9 -1.7 -1.6 -1.0 0.1 0.2 2.5 3.7 3.9
(a) Test whether there are significant differences in mean age between senior managers from
Corporation 1 and senior managers from corporation 2 using the above bootstrap data.
(b) Find a 95% confidence interval for the difference in mean age using the method of bootstrap.
Question 2
Medical researchers are interested in which of two drugs are effective in treating chronic headaches.
One set of five patients suffering from headaches received drug A for one month; another set of four
patients received Drug B. The number of pain-free days experienced by each patient is recorded
in the table below:
Pain-Free Days
Drug 1 2 3 4 5 Mean Variance
A 22 30 18 15 19 20.8 32.7
B 17 14 11 7 12.25 18.25
A bootstrap simulation was performed in which 1000 data sets of size 9 were regenerated from
the original data, and split into two groups of size 5 and 4 respectively. The resultant differences
in means (B − A) from the two groups were sorted from smallest to largest. A summary of the
differences observed at various positions in the sorted list are given as follows:
Position: 1 5 10 50 100
Value: -14.0 -11.4 -10.2 -7.1 -5.6
Position: 900 950 990 995 1000
Value: 5.3 7.1 10.2 11.0 15.7
(a) Use the bootstrapped data to estimate the p-value for the test of differences between the
means.
(b) Use the bootstrapped data to construct a 99% confidence interval for the difference between
the means.
Year: 2025 1
STA3030F Tutorial 2
Question 3
A random sample of the duration of the eruption for the Old Faithful geyser in Yellowstone National
Park, Wyoming, USA is given below:
2.0 4.6 4.2 4.4 4.0 1.8 4.5 4.0 4.5 4.3
4.1 1.8 4.3 1.9 3.5 4.8 4.8 4.0 4.6 4.1
The coefficient of variation of this data is given by cv = 0.2727506.
R was used to generate 20 bootstrap samples of size 20. The coefficients of variation were calculated
for each bootstrap sample as follows:
0.36 0.19 0.39 0.36 0.20 0.24 0.27 0.23 0.29 0.24
0.30 0.33 0.39 0.20 0.20 0.23 0.19 0.30 0.14 0.09
The sum of the above 20 coefficients of variation is 5.14.
(a) Calculate the bootstrap estimate of the bias of the sample coefficient of variation.
(b) Calculate the bootstrap bias-corrected estimate for the coefficient of variation.
(c) In your own words, explain what your answer to part (b) represents.
Question 4
Consider the distribution with the following density function:
2
(x + 1)3 , x > 0
f (x) =
0, otherwise
Simulate a random sample of values from the distribution of X using the following uniform random
numbers generated in R: 0.866 0.146 0.852.
Year: 2025 2