STAT 2263 - Winter 2024 - Practice Questions - Chapter 6 - Solutions

Below is a list of extra practice problems from a different textbook relating to the material from
Chapter 6: Confidence Intervals. Please let me know if you find any mistakes!

BD.6.3.1 Use the T-table to find the critical value (“multiplier term”) for a confidence interval based on
the following confidence levels (confidence coefficient) and sample sizes:

a) Confidence level is 0.95 and n = 15.

Solution: Confidence level = 0.95 so α = 0.05. Then, tα/2 = t0.05/2 = t0.025 . The degrees
of freedom are df = n − 1 = 15 − 1 = 14. From T-table, t14,0.025 = 2.145.

Note that this is the same as P (T14 > 2.145) = 0.025

b) Confidence level is 0.99 and n = 24.

Solution: Confidence level = 0.99 so α = 0.01. Then, tα/2 = t0.01/2 = t0.005 . The degrees
of freedom are df = n − 1 = 24 − 1 = 23. From T-table, t23,0.005 = 2.807.
c) Confidence level is 0.90 and n = 8.

Solution: Confidence level = 0.90 so α = 0.10. Then, tα/2 = t0.10/2 = t0.05 . The degrees
of freedom are df = n − 1 = 8 − 1 = 7. From T-table, t7,0.05 = 1.895.
d) Confidence level is 0.95 and n = 30.

Solution: Confidence level = 0.95 so α = 0.05. Then, tα/2 = t0.05/2 = t0.025 . The degrees
of freedom are df = n − 1 = 30 − 1 = 29. From T-table, t29,0.025 = 2.045.

Remember that if the df you are looking for is not in the table (e.g., 35, 41,
52, etc.), round down to the nearest df.

1
BD.6.3.3 A study reported the maximal nitric oxide diffusion rate in a sample of 15 asthmatic school
children as mean ± standard error of the mean and reported 3.5±0.4 n/Ls (nanoliters per
second).

a) What is the sample standard deviation?

√ √ √
Solution: SEȲ = s/ n → s = ( n)(SEȲ ) = ( 15)(0.4) = 1.55 n/Ls.

b) What is the 95% confidence interval for the mean maximal nitric oxide diffusion rate of
the population of asthmatic children?

Solution: The 95% confidence interval is given by ȳ ± t0.025 SEȲ . The degrees of freedom
are df = n − 1 = 15 − 1 = 14. From the T-table, t14,0.025 = 2.145. Thus.

ȳ ± t14,0.025 SEȲ
3.5 ± (2.145)(0.4) → (2.64, 4.36)

c) What assumptions are necessary for the validity of the confidence interval you constructed?

Solution: Since n < 30, we can’t apply the CLT and assume that the sampling dis-
tribution of the sample mean is approximately normal. So, for the CI to be valid, we
have to assume that the distribution of maximal nitric oxide diffusion rate in asthmatic
schoolchildren is approximately normally distributed. We also need to assume that the
sample is a random sample from the population.

d) Interpret the confidence interval calculated in b).

Solution: We expect the mean maximal nitric oxide diffusion rate in asthmatic school
children to be between 2.64 and 4.36 nL/s, and we expect the true mean to be found in
95% of such studies.

2
1. The 2010 General Social Survey asked the question “For how many days during the past 30
days was your mental health, which includes stress, depression, and problems with emotions,
not good?” Based on responses from 1151 US residents, the survey reported a 95% confidence
interval of 3.40 to 4.24 days in 2010.

a) What is the parameter of interest?

Solution: The parameter of interest is the mean number of days during the past 30 days
that US residents said their mental health was not good.

b) Interpret the confidence interval in the context of the data.

Solution: We expect that the mean number of days during the past 30 days that US
residents say their mental health is not good in 2010 to be between 3.40 and 4.24 days,
and we expect the true mean number of days to be found in 95% of such studies.

c) What does “95% confident” mean? Explain in the context of the application

Solution:his means that if we were to repeatedly sample from this population (US resi-
dents) and calculate a 95% confidence interval for this parameter (mean number of days
during the past 30 days that US residents said their mental health was not good), then
we would expect approximately 95% of these confidence intervals to contain the true
parameter value. For example, in 1000 samples from this population, we would expect
approximately 950 of the confidence intervals to contain the true mean.

d) If a new survey were to be done with 500 Americans, would the standard error of the
estimate be larger, smaller, or about the same? Assume the standard deviation has
remained constant since 2010.
√
Solution: SEȲ = s/ n. So, if n decreases from 1000 to 500, we would expect the
standard error to increase.

3
BD.6.4.7 Twenty-four experimental animals with vitamin D deficiency were divided equally into two
groups. Group 1 received treatment consisting of a diet that provided vitamin D. The second
group was not treated. At the end of the experimental period, serum calcium determinations
were made with the following results: Assume normally distributed populations with unequal

variances.

a) Construct a 99% confidence interval for the difference between population means.

Solution: A 99% CI is given by (ȳ1 − ȳ2 ) ± t0.005 SEȲ1 −Ȳ2 . The degrees of freedom are
approximated by df = n1 + n2 − 2 = 24 − 2 = 22. From the T-table, t22,0.005 = 2.819.
Thus,

(ȳ1 − ȳ2 ) ± t22,0.005 SEȲ1 −Ȳ2

s
s21 s2
(ȳ1 − ȳ2 ) ± t22,0.005 + 2
n1 n2
r
1.52 2.02
(11.1 − 7.8) ± (2.819) +
12 12
3.3 ± (2.819)(0.7216878)
3.3 ± 2.034438 → (1.27, 5.33)

Note: you could have constructed this using (ȳ2 − ȳ1 ) as the point estimate. This would
give you the same confidence interval but with negative values (i.e., (−5.33, −1.27). The
interpretation is slightly different as this is the difference in means among the untreated
vs. treated.

b) Interpret the confidence interval in a).

Solution: We expect the difference in mean serum calcium level among treated animals
compared to untreated animals to be between 1.27 and 5.33 mg/100 ml, and we expect
the true difference in means to be found in 99% of such studies.

4
 c) Confirm your answer in part a) using Minitab.

Solution: Using the 2-sample t procedure in Minitab:

Note that the CI from Minitab may be slightly difference because of 1) rounding and 2) we
are calculating the CI by hand using an approximation of the exact degrees of freedom. The
degrees of freedom formula is lengthy, you can find it 6.7.1, but this is what Minitab is using.

Also, to change the confidence level (default it 95%) click options in the 2-sample t procedure.

d) Based on the confidence interval, does it appear likely that the populations means are different?
Explain your answer.

Solution: The 99% confidence interval does not contain the null value of 0 (i.e., the value we
would expect if the population means were equal). This means that 0 is not within the range
of plausible values for this parameter. Thus, it seems likely that the mean serum calcium levels
in these two populations (treated and untreated animals) are different.