1.

Fill in the black

1.1. The process of using sample statistics to draw conclusions about true population
parameters is called Statistical Inference

1.2. A summary measure that is computed to describe a characteristic from only a sample
of the population is called Statistic

1.3. Which of the following is not an element of descriptive statistical

problems?

a) an inference made about the population based on the sample

b) the population or sample of interest
c) tables, graphs, or numerical summary tools
d) identification of patterns in the data

1.4 Which of the following is NOT a reason for the need for sampling?

a) It is usually too costly to study the whole population.

b) It is usually too time consuming to look at the whole
population.
c) It is sometimes destructive to observe the entire population.
d) It is always more informative to investigate a sample than
the entire population.

1.5 Which of the 4 methods of data collection is involved when a person

records the use of the Los Angeles freeway system?

a) published sources
b) experimentation
c) surveying
d) observation

1.6 The most frequently occurring data value is Mode

2. What is the sample space for choosing a prime number less than 30 at random?

{2, 3, 5, 7, 11, 13, 17, 19, 23, 29}

3. A student buys 3000 integrated circuits (ICs) from supplier A, 5000 ICs from supplier
B and 2000 ICs from supplier C. He tested the ICs and found that the conditional
probability of an IC being defective depends on the supplier from it was bought.
Specifically, given that an IC came supplier A, the probability that it is defective is 0.15;
given that an IC came supplier B, the probability that it is defective is 0.2; given that an
IC came supplier C, the probability that it is defective is 0.25. If ICs from the three
supplier are mixed together and one is selected at random, what is the probability that it is
defective?

Defective ICs from supplier A = 0.15 * 3000 = 450

Defective ICs from supplier B = 0.2*5000 = 1000

Defective ICs from supplier C = 0.25*2000 = 500

P(X) = (450 + 1000 + 500) / (3000 + 5000 + 2000) = 0.195

4. Disks of polycarbonate plastic from a supplier are analyzed for scratch and shock
resistance. The results from 100 disks are summarized as follows:

Shock Resistance
Scratch Resistance High Low
High 50 11
Low 80 15
Let A denote the event that a disk has no high shock resistance, and let B denote the
event that a disk has high scratch resistance. If a disk is selected at random, determine the
probability P(B|A)

P(B|A) = 11 / (11 + 15) = 0.423

5. Let the random variable X be a Poisson distribution with mean of 4.21. Find the
probability that X = 4.

X ~ P(4.21)

P(X=4) = e-4.21 * 4.214 / 4! = 0.194

6. Find the mean and variance of the given probability distribution.

x P(x)
0 0.1
1 0.2
2 0.1
3 0.3
4 ?
P(4) = 0.3

Mean = 2.5

Var = 1.85

7. If X is discrete uniform distributed over the interval [50,100]. Compute the probability
that 20 < X < 80.

f = 1 / 51

P(20 < X < 80) = (80 – 50) * 1/51 = 30/51 = 0.59

8. The probability that a radish seed will germinate is 0.1. A gardener plants seeds in
batches of 1120. Find the standard deviation for the number of seeds germinating in each
batch.

X ~ B(1120, 0.1)

Var = 1120*0.1*0.9 = 100.8

Stdev = sqrt(100.8) = 10.0399

9. Let X be a continuous uniform distribution over the interval [1,10]. Find the mean and
variance of X.

X ~ U(1, 10)

Mean = (1 + 10) / 2 = 5.5

Var = (10 – 1)^2 / 12 = 6.75

10. If X is a continuous random variable with probability density function f( x ) = cx2 , 0

< x <2 . Find the mean and the variance of X.

c = 3/8

mean = 3/2 = 1.5

var = 3/20 = 0.15

11. Let the random variable X represent the profit made on a randomly selected day by a
certain store. Assume that X is Normal with mean 450 and standard deviation 20.
Compute P(X > 460) and P(455>X > 440)

X ~ N(450, 20^2)

P(X>460) = P(Z > 0.5) = 1 – phi(0.5) = 0.30854

P(455>X>440) = P(0.25 > Z > -0.5) = phi(0.25) – phi(-0.5) = 0.29017

12. Ten measurements were made on the inside diameter of forged piston rings used in an
automobile engine. The data (in millimeters) are 7; 7.4; 7.5; 7.2; 7.8; 7.6; 7.4;7.1; 7.9 and
7.3. Calculate the mean and sample standard deviation

Mean = 7.42

Stdev = 0.2898

13. Suppose that sample of size n = 15 are selected at random a normal population with
mean 80 and standard deviation 30. What is the probability that the sample mean falls in
the interval from 75 to 84?

X ~ N(80, 30^2)

Mean X ~ N(80, 30^2 / 15)

P(75 < Mean X < 84) = P (-0.645 < Z < 0.516) = 0.43761

14. Suppose that a random variable X has a continuous uniform distribution with f(x)=0.1
, where x is in [0,10]. Find the mean and variance of the sample mean of a random
sample of size n = 40

X ~ U(0, 10)

Mean = (0 + 10) / 2 = 5

Var = (10 – 0)^2 / 12 * 0.1= 8.333 5/24

15. A normal population has mean 1200 and variance 150. How large must the random
sample be if we want the standard error of the sample mean to be 2.8?

X ~ N(1200, 150)

SE mean = 2.8 = sqrt(150 / n) => n = 19,13

16. The diameter of holes for a cable harness is known to have a normal distribution with
standard deviation 0.1 inch. A random sample of size 25 yield an average diameter of
12.3 inch. Find a 94% two - side confidence interval on the mean hole diameter.

X ~ N(mean, 0.1^2)

N = 25

mean x = 12.3

alpha = 0.06 => Z(0.03) = 1.885

error = 1.885 * 0.1 / sqrt(25) = 0.0377

=> (12.3 – 0.0377; 12.3 + 0.0377)

17. An article describes the effect of delamination on the natural frequency of beams
made from composite laminates. Six such delaminated beams were subjected to loads,
and the resulting frequencies were as follows (in hertz): 23; 24; 23.5; 22; 24.5 and 23.5.
Calculate a 98% two - sided confidence interval on mean natural frequency.

n=6

s = 0.86

Mean x = 23.417

Alpha = 0.02 => t(5, 0.01) = 3.365

Error = 3.365 * 0.86 / sqrt(6) = 1.18

 (23.417 – 1.18; 23.417 + 1.18)

18. Of 1000 randomly selected cases of lung cancer, 450 resulted in death within 5 years.
Calculate a 96% CI on the death rate from lung cancer.

n = 1000

f = 450 / 1000 = 0.45

alpha = 0.04 => Z(0.02) = 2.055

error = 2.055 * sqrt(0.45 * (1 – 0.45)) / sqrt(1000) = 0.032

=> (0.45 – 0.032; 0.45 + 0.032)

19. An economist is interested in studying the incomes of consumers in a particular
region. The population standard deviation is known to be 250 (USD). A random sample
of 50 individuals resulted in an average income of 1000 (USD). What total sample size
would the economist need to use for a 99.5% confidence interval if the width of the
interval should not be more than 30 (USD)?

σ = 250

n = 50

mean x = 1000

alpha = 0.005 => Z(0.0025) = 2.81

2 * error <= 30

2 * 2.81 * 250 / sqrt(n) <= 30

n >= 2193.36

20. The daily intakes of milk (in ounces) for ten randomly selected people were: 123;
329; 331; 263; 108; 268; 274; 297; 190; 299. Find a 95% confidence interval for the
population standard deviation σ.

n = 10

s = 80.51

alpha = 0.05

(10 – 1) * 80.51^2 / X(0.025) <= σ^2 <= (10 – 1) * 80.51^2 / X(0.975)

 3066.6 <= σ^2 <= 21606.2

=> 55.4 <= σ <= 146.99

21. An engineer who is studying the tensile strength of a steel alloy intended for use in
golf club shafts knows that tensile strength is approximately normally distributed with
standard deviation 10 psi. A random sample of 25 specimens has a mean tensile strength
of 39 psi. Test the hypothesis that mean strength is 45 psi. Use α=0.01.

σ = 10

n=25
mean x = 39

α=0.01

H0: mean = 45

H1: mean != 45

Z = (39 – 45) * sqrt(25) / 10 = -3

Z(0.005) = 2.575

|Z| > Z(0.005) => reject H0

22. A random sample of 350 circuits generated 30 defectives. Use the data to test
H0:p=0.1 versus H1:p>0.1

n=350

f=30/350 = 0.0857

alpha = 0.05

H0: p = 0.1

H1: p > 0.1

Z = (0.0857-0.1)*sqrt(350)/sqrt(0.1*(1-0.1)) = -0.89

Z(0.025) = 1.96
|Z| < Z(0.025) => accept H0

23. The mean water temperature downstream from a power plant cooling tower discharge
pipe should be no more than 100°F. Past experience has indicated that the standard
deviation of temperature is 2°F. The water temperature is measured on ten randomly
chosen days, and the average temperature is found to be 97°F. Test the hypotheses H 0:μ =
100, H1:μ < 100 by using p_value

σ=2

n=10

mean x = 97

alpha = 0.05
H0:μ = 100

H1:μ < 100

Z = (97 – 100) * sqrt(10) / 2 = -4.74

Pvalue(Z)= phi(-4.74) = 0 < 0.05 => reject H0

24. What are type I error and type II error?

type I error: when H0 is true and we reject it

type II error: when H0 is false and we accept it

25. An Izod impact test was perform on 25 specimens of PVC pipe. The sample standard
deviation was 2.2 Test H0: σ = 2, H1: σ ≠ 2, using α = 0.05.

n=25

s=2.2

α =0.05

H0: σ = 2

H1: σ ≠ 2

X = (25 – 2) * 2.2^2 / 2^2 = 27.83

X(24, 0.025) = 39.364

X(24, 0.975) = 12.401

=> accept H0

26. Which correlation coefficient represents the weakest association between the X and Y
variables?

Select one:

(a) r = 0.50

(b) r = -0.20

(c) r = 0.90

(d) r = 0.10
27. A random sample of n=38 observations was made on the time to failure of an
electronic component and the temperature in the application environment in which the
component was used. Given that r = 0.35 Test the hypothesis that H0: ρ = 0 versus H1: ρ ≠
0 with α=0.05

n=38

r=0.35

α=0.05

H0: ρ = 0

H1: ρ ≠ 0

t = 0.35 * sqrt(38-2) / sqrt(1-0.35^2) = 2.24

t(36, 0.025) = Z(0.025) = 1.96

|t| > Z(0.025) => reject H0

28. The paired data below consist of the test scores of 6 randomly selected students and
the number of hours they studied for the test.

Hours 5 10 15 20 10 5

Score 4 8 10 12 9 3

28.1 Find the value of the linear correlation coefficient r

r= 0.944

28.2 Find the equation of the regression line.

y = 1.54 + 0.57x + error

28.3 Test the hypothesis that H0: ρ = 0 versus H1: ρ ≠ 0 with α=0.05

t = 0.944 * sqrt(6-2) / sqrt(1-0.944^2) = 5.722

t(4, 0.025) = 2.776

|t| > t(4, 0.025) => reject H0

29. An Izod impact test was perform on 20 specimens of PVC pipe. The sample standard
deviation was 0.25. Test H0: σ = 0.1, H1: σ ≠ 0.1, using α = 0.01.
Let X20.005,19 = 38.58; X20.995,19 = 6.84.

n=20

s=0.25

α =0.01

H0: σ = 0.1

H1: σ ≠ 0.1

X = (20 – 1) * 0.25^2 / 0.1^2 = 118.75

=> reject H0

30. A random sample of 310 circuits generated 15 defectives. Use the data to test
H0:p=0.05 versus H1:p≠0.05.Let z0.025=1.96; use α =0.05.

n=310

f=15/310=0.048

Z = (0.048 – 0.05) * sqrt(310) / sqrt(0.05 * (1-0.05)) = -0.16

|Z| < z0.025 => accept H0

31. An engineer who is studying the tensile strength of a steel alloy intended for use in
golf club shafts knows that tensile strength is approximately normally distributed with
standard deviation 50 psi. A random sample of 16 specimens has a mean tensile strength
of 3450 psi. Test the hypothesis that mean strength is 3500 psi. Use α=0.01. Let
z0.005=2.58; z0.1=1.29.

σ = 50

n=16

mean x = 3450

α=0.01

H0: mean = 3500

H1: mean != 3500

Z = (3450 - 3500) * sqrt(16) / 50 = -4

|Z| > Z(0.005) => reject H0