CHAPTER 6: Distributionsofsamplingstatistics

Problems
1. Suppose that X1 , X2 , X3 are independent with the common probability
mass function

P {Xi = 0} = .2, P {Xi = 1} = .3, P {Xi = 3} = .5, i = 1, 2, 3

X1 + X2
a. Plot the probability mass function of X 2 = .
2
b. Determine E[X 2 ] and Var(X 2 ).
X1 + X2 + X3
c. Plot the probability mass function of X 3 = .
3
d. Determine E[X 3 ] and Var(X 3 ).
2. If 10 fair dice are rolled, approximate the probability that the sum of
the values obtained (which ranges from 10 to 60) is between 30 and 40
inclusive.
3. Approximate the probability that the sum of 16 independent uniform (0,
1) random variables exceeds 10.
4. A roulette wheel has 38 slots, numbered 0, 00, and 1 through 36. If you
bet 1 on a specified number, you either win 35 if the roulette ball lands
on that number or lose 1 if it does not. If you continually make such bets,
approximate the probability that
a. you are winning after 34 bets;
 Problems 239

b. you are winning after 1000 bets;

c. you are winning after 100,000 bets.
Assume that each roll of the roulette ball is equally likely to land on any
of the 38 numbers.
5. A highway department has enough salt to handle a total of 80 inches of
snowfall. Suppose the daily amount of snow has a mean of 1.5 inches
and a standard deviation of .3 inch.
a. Approximate the probability that the salt on hand will suffice for the
next 50 days.
b. What assumption did you make in solving part (a)?
c. Do you think this assumption is justified? Explain briefly.
6. Fifty numbers are rounded off to the nearest integer and then summed.
If the individual roundoff errors are uniformly distributed between −.5
and .5, what is the approximate probability that the resultant sum differs
from the exact sum by more than 3?
7. A six-sided die, in which each side is equally likely to appear, is repeatedly
rolled until the total of all rolls exceeds 400. Approximate the probability
that this will require more than 140 rolls.
8. The amount of time that a certain type of battery functions is a random
variable with mean 5 weeks and standard deviation 1.5 weeks. Upon
failure, it is immediately replaced by a new battery. Approximate the
probability that 13 or more batteries will be needed in a year.
9. The lifetime of a certain electrical part is a random variable with mean
100 hours and standard deviation 20 hours. If 16 such parts are tested,
find the probability that the sample mean is
a. less than 104;
b. between 98 and 104 hours.
10. A tobacco company claims that the amount of nicotine in its cigarettes
is a random variable with mean 2.2 mg and standard deviation .3 mg.
However, the sample mean nicotine content of 100 randomly chosen
cigarettes was 3.1 mg. What is the approximate probability that the sam-
ple mean would have been as high or higher than 3.1 if the company’s
claims were true?
11. The lifetime (in hours) of a type of electric bulb has expected value 500
and standard deviation 80. Approximate the probability that the sample
mean of n such bulbs is greater than 525 when
a. n = 4;
b. n = 16;
c. n = 36;
d. n = 64.
12. An instructor knows from past experience that student exam scores have
mean 77 and standard deviation 15. At present the instructor is teaching
two separate classes — one of size 25 and the other of size 64.
a. Approximate the probability that the average test score in the class
of size 25 lies between 72 and 82.
240 C H AP TE R 6: Distributions of sampling statistics

b. Repeat part (a) for a class of size 64.

c. What is the approximate probability that the average test score in
the class of size 25 is higher than that of the class of size 64?
d. Suppose the average scores in the two classes are 76 and 83. Which
class, the one of size 25 or the one of size 64, do you think was more
likely to have averaged 83?
13. If X is binomial with parameters n = 150, p = .6, compute the exact value
of P {X ≤ 80} and compare with its normal approximation both (a) mak-
ing use of and (b) not making use of the continuity correction.
14. Teams 1, 2, 3, 4 are all scheduled to play with each of the other teams 10
times. Whenever team i plays team j , team i is the winner with probabil-
ity Pi,j , and team j is the winner with probability Pj,i = 1 − Pi,j . If

P1,2 = .6, P1,3 = .7, P1,4 = .75,

P2,3 = .6, P2,4 = .70, P3,4 = .5,

a. approximate the probability that team 1 wins at least 20 games.

Suppose we want to approximate the probability that team 2 wins at
least as many games as does team 1. To do so, let X be the number
of games that team 2 wins against team 1, let Y be the total number
of games that team 2 wins against teams 3 and 4, and let Z be the
total number of games that team 1 wins against teams 3 and 4.
b. Are X, Y, Z independent?
c. Express the event that team 2 wins at least as many games as does
team 1 in terms of the random variables X, Y, Z.
d. Approximate the probability that team 2 wins at least as many games
as team 1.
15. A club basketball team will play a 60-game season. Thirty-two of these
games are against class A teams and 28 are against class B teams. The out-
comes of all the games are independent. The team will win each game
against a class A opponent with probability .5, and it will win each game
against a class B opponent with probability .7. Let X denote its total num-
ber of victories in the season.
a. Is X a binomial random variable?
b. Let XA and XB denote, respectively, the number of victories against
class A and class B teams. What are the distributions of XA and XB ?
c. What is the relationship between XA , XB , and X?
d. Approximate the probability that the team wins 40 or more games.
16. Argue, based on the central limit theorem, that a Poisson random vari-
able having mean λ will approximately have a normal distribution with
mean and variance both equal to λ when λ is large. If X is Poisson with
mean 100, compute the exact probability that X is less than or equal to
116 and compare it with its normal approximation both when a conti-
nuity correction is utilized and when it is not. The convergence of the
Poisson to the normal is indicated in Figure 6.4.
 Problems 241

FIGURE 6.4
Poisson probability mass functions.
242 C H AP TE R 6: Distributions of sampling statistics

17. Use the text disk to compute P {X ≤ 10} when X is a binomial random
variable with parameters n = 100, p = .1. Now compare this with its (a)
Poisson and (b) normal approximation. In using the normal approxi-
mation, write the desired probability as P {X < 10.5} so as to utilize the
continuity correction.
18. The temperature at which a thermostat goes off is normally distributed
with variance σ 2 . If the thermostat is to be tested five times, find
a. P {S 2 /σ 2 ≤ 1.8}
b. P {.85 ≤ S 2 /σ 2 ≤ 1.15}
where S 2 is the sample variance of the five data values.
19. In Problem 18, how large a sample would be necessary to ensure that the
probability in part (a) is at least .95?
20. Consider two independent samples — the first of size 10 from a normal
population having variance 4 and the second of size 5 from a normal
population having variance 2. Compute the probability that the sample
variance from the second sample exceeds the one from the first. (Hint:
Relate it to the F-distribution.)
21. Twelve percent of the population is left-handed. Find the probability that
there are between 10 and 14 left-handers in a random sample of 100
members of this population. That is, find P {10 ≤ X ≤ 14}, where X is the
number of left-handers in the sample.
22. Fifty-two percent of the residents of a certain city are in favor of teaching
evolution in high school. Find or approximate the probability that at
least 50 percent of a random sample of size n is in favor of teaching
evolution, when
a. n = 10;
b. n = 100;
c. n = 1000;
d. n = 10,000.
23. The following table gives the percentages of individuals of a given city,
categorized by gender, that follow certain negative health practices. Sup-
pose a random sample of 300 men is chosen. Approximate the probabil-
ity that
a. at least 150 of them rarely eat breakfast;
b. fewer than 100 of them smoke.

Sleeps 6 Hours Smoker Rarely Eats Is 20 Percent

or Less per Breakfast or More
Night Overweight
Men 22.7 28.4 45.4 29.6
Women 21.4 22.8 42.0 25.6
Source: U.S. National Center for Health Statistics, Health Promotion and Disease Prevention.

24. (Use the table from Problem 23.) Suppose a random sample of 300
women is chosen. Approximate the probability that
 Problems 243

a. at least 60 of them are overweight by 20 percent or more;

b. fewer than 50 of them sleep 6 hours or less nightly.
25. (Use the table from Problem 23.) Suppose random samples of 300
women and of 300 men are chosen. Approximate the probability that
more women than men rarely eat breakfast.
26. The following table uses data concerning the percentages of teenage male
and female full-time workers whose annual salaries fall in different salary
groupings. Suppose random samples of 1000 men and 1000 women were
chosen. Use the table to approximate the probability that
a. at least half of the women earned less than $20,000;
b. more than half of the men earned $20,000 or more;
c. more than half of the women and more than half of the men earned
$20,000 or more;
d. 250 or fewer of the women earned at least $25,000;
e. at least 200 of the men earned $50,000 or more;
f. more women than men earned between $20,000 and $24,999.

Earnings Range Percentage of Percentage of Men

Women
$4999 or less 2.8 1.8
$5000 to $9999 10.4 4.7
$10,000 to $19,999 41.0 23.1
$20,000 to $24,999 16.5 13.4
$25,000 to $49,999 26.3 42.1
$50,000 and over 3.0 14.9
Source: U.S. Department of Commerce, Bureau of the Census.

27. Today, roughly 10.5 percent of the labor force belong to a union. If five
workers are randomly chosen, what is the probability that none of them
belong to a union? Compare your answer to what it would have been in
1983 when 20.1 percent of the workforce belonged to a union.
28. The sample mean and sample standard deviation of all San Francisco
student scores on the most recent Scholastic Aptitude Test examination
in mathematics were 517 and 120. Approximate the probability that a
random sample of 144 students would have an average score exceeding
a. 507;
b. 517;
c. 537;
d. 550.
29. The average salary of newly graduated students with bachelor’s degrees
in chemical engineering is $53,600, with a standard deviation of $3200.
Approximate the probability that the average salary of a sample of 12
recently graduated chemical engineers exceeds $55,000.
244 C H AP TE R 6: Distributions of sampling statistics

30. A certain component is critical to the operation of an electrical system

and must be replaced immediately upon failure. If the mean lifetime of
this type of component is 100 hours and its standard deviation is 30
hours, how many of the components must be in stock so that the proba-
bility that the system is in continual operation for the next 2000 hours is
at least .95?