MAT 2377C

Final exam

December 10, 2010

Time: 180 minutes

Professor: Rafal Kulik

Student Number:
Family Name:
First Name:

This is an open book examination.

Only non-programmable and non-graphic calculators are permitted.
Record your answer to each question in the table below.
Number of pages: 7 (including this one).
Number of questions: 24.
NOTE: At the end of the examination, hand in only this page. You may keep the questionnaire.

Question
1
2
3
4
5
6
7
8
9
10
11
12

Answer

Question
13
14
15
16
17
18
19
20
21
22
23
24

Answer

Q1. Suppose that for a very large shipment of integrated-circuit chips, the probability of failure for any one chip is
0.09. Find the probability that at most 2 chips fail in a random sample of size 20. (The numbers are rounded
down to the second decimal place).
(a)

0.13

(b)

0.90

(c)

0.73

(d)

0.20

(e)

none of the preceding

Solution to Q1:
X B(20, 0.09). So
P (X 2)

20
0

(.09)0 (.91)20 +

20
1

(.09)1 (.91)19 +

20
2

(.09)2 (.91)18 = 0.73

Q2. A scientist inoculates several mice, one at a time, with a disease germ until he finds one that has contracted the
disease. If the probability of contracting the disease is 1/6, what is the probability that 8 mice are required?
(The numbers are rounded down to the fourth decimal place).
(a)

0.0465

(b)

0.9350

(c)

0.0740

(d)

0.2600

(e)

none of the preceding

Solution to Q2:
X = # number of mice required to observe the first one with the disease. X is geometric with p = 1/6. So
P (X = 8) = (1 p)7 p = 0.0465

Q3. Assume that random variables X and Y are independent and have distribution X Poisson(2) and Y
B(5, 0.2), respectively. Compute
P ({X = 0} or {Y = 0}) = P ({X = 0} [ {Y = 0}) .

(The numbers are rounded up to the fourth decimal place)

(a)

0.4325

(b)

0.5621

(c)

0.4630

(d)

0.4187

(e)

insufficient information provided

Solution to Q3:
P ({X = 0} or {Y = 0})

= P ({X = 0}) + P ({Y = 0})

= P ({X = 0}) + P ({Y = 0})
=

exp( 2) + 0.20 0.85

P ({X = 0} and {Y = 0})

P ({X = 0}) P ({Y = 0})

exp( 2) 0.20 0.85 = 0.4187

Q4. A medical research team wished to evaluate a proposed screening test for Alzheimers disease. The test was
given to a random sample of 450 patients with Alzheimers disease, in 436 cases the test result was positive.
Also, the test was given to a random sample of 500 patients without the disease, only in 5 cases the result was
positive. It is known that in the Canada 7.7% of the population aged 65 and over have Alzheimers disease.

Find the probability that a person has the disease given that the test was positive. (The numbers are rounded
down to the second decimal place).
(a)

0.97

(b)

0.88

(c)

0.99

(d)

0.12

(e)

none of the preceding

Solution to Q4:
A - test positive, D - a person has disease. Given: P (A|D) =
P (Dc |A) (Bayes formula):
P (D|A) =

436
5
, P (A|Dc ) =
, P (D) = 0.077. To find:
450
500

P (A|D)P (D)
= 0.88.
P (A|D)P (D) + P (A|Dc )P (Dc )

Q5. Consider the following system with four components. We say that it is functional if there exists a path of
functional components from left to right. The probability of each component functions is shown. Assume that
the components function or fail independently. What is the probability that the system operates? (The numbers
are rounded down to the second decimal place).
2
0.7

3
0.4

1
0.5
4
0.5
(a)

0.32

(b)

0.16

(c)

0.03

(d)

0.68

(e)

none of the preceding

Solution to Q5:
Call Box B - components 2,3,4, Box C - components 2,3.
P (Box C operates)

= P (component 2 operates and component 3 operates)

= P (component 2 operates)P (component 3 operates) = 0.4 0.7 = 0.28.

P (Box B operates)

= P (Box C operates or component 4 operates)

= P (Box C operates) + P (component 4 operates)
P (Box C operates)P (component 4 operates)
= 0.28 + 0.5 0.28 0.5 = 0.64.

P (system operates) = P (component 1 and Box B operate)

= P (component 1 operates)P (Box B operates)
= 0.5 0.64 = 0.32.

Q6. A material is studied for a possible contamination. Suppose that occurrences of contaminated particles can be
described by a Poisson process with the intensity 0.02 particles per kilogram. Find the probability that there
will be no contaminated particles in 10 kilograms of the material.
(a)

0.989

(b)

0.819

(c)

0.135

(d)

0.020

(e)

none of the preceding

Q7. In a NiCd battery, a fully charged cell is composed of Nickelic Hydroxyde. Nickel is an element that has a
multiple oxidation states. Let X be the nickel charge, which has the following probability mass function:
x fX (x)
0
.18
2
.34
4
.33
10
k
where k is an unique number. Determine the mean and the standard deviation of the nickel charge. (The
numbers are rounded down to the third decimal place).
(a)

3.064; 3.5

(b)

3.5; 9.390

(c)

3.5; 3.064

(d)

4; 7.250

(e)

none of the preceding

Q8. Let X be a continuous random variable with mean X = .75 and probability density function
fX (x) = 3 x2 , 0 < x < 1.
Give the variance of the random variable X. (The numbers are rounded down to the fourth decimal place).
(a)

0.0375

(b)

0.1936

(c)

0.7746

(d)

0.3873

(e)

none of the preceding

Solution to Q8:
E[X ] =
2

x2 (3 x2 ) dx = 0.6 )

2
X

= E[X 2 ]

2X = 0.0375

Q9. Assume that Xi , i = 1, . . . , 81, are independent random variables with

! a common density function fX (x) =
81
X
exp( x), x > 0. Find the approximate probability P
Xi > 90 . Hint: Central Limit Theorem. (The
numbers are rounded down to three decimal place).

i=1

(a)

0.644

(b)

0.168

(d)

0.158

(e)

none of the preceding

(c)

0.346

Solution to Q9:
E(X) = 1, Var(X) = 1. So
n
X
P(
Xi > 90)
i=1

= P

P81

Xi 81 1
90 81
p
> p
81 1
81

i=1

= P (Z0 > 1) = 1

0.67 = 0.1586

Q10. A random sample of size n1 = 16 is selected from a normal population with a mean of 75 and variance of 288.
A second random sample of size n2 = 9 is taken independently from another normal population with mean 80
1 and X
2 be the two sample means. Find the probability that X
1 + X
2 exceeds
and variance of 162. Let X
156.5. (The numbers are rounded down to the fourth decimal place).
(a)

0.5987

(b)

0.4012

(c)

0.6231

(d)

0.4235

(e)

none of the preceding

Solution to Q10:
X 1 + X 2 N (75 + 80, 288/16 + 162/9) = N (155, 36).
P (X 1 + X 2 > 156.5) = P (Z >

156.5
p

155
36

)=1

(0.027) = 0.4012.

Q11. The city of Ottawa would like to know how many people are in favor of an increase in a property tax. 1000
residents have been asked and 300 answered Yes, I favor a property tax increase. A 95% confidence interval
for the proportion of people, who are in favor of property tax increase, is
(a)

[0.202,0.254]

(b)

[0.197,0.259]

(c)

[0.194,0.262]

(d)
[0.272,0.328]
(e)
none of the preceding
(The lower limit was rounded up to the third decimal place; The upper limit was rounded down to the third
decimal place).
Solution to Q11:
pb z.025

So [0.272, 0.328].

r
pb (1 pb)
300
300/1000 (1 300/1000)
=
1.96
n
1000
1000

Q12. A machine is producing metal pieces that are cylindrical in shape. A sample of pieces is taken and the diameters
are
1.01 0.97 1.03 1.04 0.99
0.98 0.99 1.01 1.03
The sample mean and standard deviation are x = 1.00556 and s = 0.02455, respectively. Find a 95% confidence
interval for the true mean diameter. Assume that the population is normally distributed.
(a)

[0.989,1.022]

(b)

[0.987,1.024]

(c)

[0.978,1.033]

(d)
[0.991,1.034]
(e)
none of the preceding.
(The lower limit was rounded up to the third decimal place; The upper limit was rounded down to the third
decimal place).
Solution to Q12:
We have t.025,9

= 2.306. So

s
x 2.306 p = [0.987, 1.024].
n

Q13. Past experience has indicated that the breaking strength of yarn used in manufacturing drapery material is
normally distributed and that = 2. A random sample of twenty five specimens is tested and the average
breaking strength is found to be x
= 98 psi. Find a 99% confidence interval on the true mean breaking strength.
(a)

[97.216,98.784]

(b)

[97.216,98.554]

(c)

[96.972,99.028]

(d)
[97.446,98.554]
(e)
none of the preceding
(The lower limit was rounded up to the third decimal place; The upper limit was rounded down to the third
decimal place).
Solution to Q13:
Conditions: normal population with known .
A 95% confidence interval is
x z.025 p = 98 1.96
n

2
p
25

= [97.216, 98.784].

Q14. We want to test the hypothesis that the average content of containers of a particular lubricant is more than 10
liters if the contents of a random sample of 10 containers are
10.2 9.7 10.1 10.5 10.1
11.1 9.9 10.4 10.4 9.5
Find the P -value of the one-sided test. Assume that the distribution of contents is normal. Hint: for this data
we have
10
10
X
X
xi = 101.9 and
x2i = 1040.19.
i=1

i=1

(a)

0.05 < P < 0.10

(b)

0.10 < P < 0.20

(d)

0.50 < P < 0.80

(e)

none of the preceding

(c)

0.25 < P < 0.40

Solution to Q14:
We test H0 : = 10 vs. H1 : > 10. We have x = 10.19 and s = 0.45. The observed value of test statistics is
t0 =

x 10
p = 1.332809
s/ n

The P -value is P (T > 1.332) and is between 0.1 and 0.2, see Table V with = n

1 = 9. Answer (B).

Q15. The melting point of each of 16 samples of certain brand of vegetable oil was determined, resulting in x
= 94.32.
Assume that the distribution of melting point is normal with = 1.2. Test H0 : = 95 versus H1 : 6= 95
with = 0.01. Determine the P -value and state your conclusion.
(a)
Reject H0 , P -value=0.012
(b)

Can not reject H0 , P -value=0.023

(c)

Reject H0 , P -value=0.023

(d)

Can not reject H0 , P -value=0.012.

Solution to Q15:

The observed value of test statistics is

z0 =

95
94.32 95
p =
p
=
/ n
1.2/ 16

Since alternative is two-sided, P -value= 2P (Z <

reject H0 .

2.27.

2.27) = 2 (1

(2.27)) = 0.023. Since P > , we do not

Q16. An expert wishes to determine the average time (in seconds) that it takes to drill holes in a certain metal clamp.
How large a sample is required to be 99% confident that the sample mean will be within 15 seconds of the true
mean. Assume that it is known from previous studies that = 30 seconds.
(a)

26

(b)

27

(c)

28

(d)

29

(e)

none of the preceding

Solution to Q16:
n
So n = 27 observations.

hz

.005

i2

(2.576) (30)
15

= 26.5

Q17. Assume that we have a sample of size 10 from a population N (4, 9). Denote by X and S 2 , the sample mean
and sample variance, respectively. Find c such that

X 4
p c = .95.
P
S/ 10
(a)

1.833

(b)

1.86

(c)

(d)

2.262

(e)

none of the preceding

1.645

Solution to Q17:
Equivalent statement: find c such that
P

X 4
p
S/ 10

X 4
p has Student distribution with n
S/ 10
that P (t9 > 1.833) = 0.05, thus c = 1.833.
We have that

c = 0.05.
1 = 9 degrees of freedom. From the table we read

Q18. The data below are from Darwins study of cross- and self-fertilization. Pairs of seedlings of the same age, one
produced by cross-fertilization and the other by self-fertilization, were grown together so that the members of
each pair were treated under nearly identical conditions. The data are the final heights of each plant after a
fixed period of time, in inches. Darwin consulted the famous 19th century statistician Francis Galton about the
analysis of these data.
pair crossfertilized selffertilized
1
23.5
17.4
2
12.0
20.4

3
4
5
6
7
8
9
10
11
12
13
14
15

21.0
22.0
19.1
21.5
22.1
20.4
18.3
21.6
23.3
21.0
22.1
23.0
12.0

20.0
20.0
18.4
18.6
18.6
15.3
16.5
18.0
16.3
18.0
12.8
15.5
18.0

Assuming the heights are normally distributed, we conduct the test of no dierence between fertilization method
(two-sided alternative). Then
(a)
P -value 2 (0.05, 0.1); do not reject H0 for = 0.01;
(b)
(c)
(d)
(e)

P -value 2 (0.05, 0.1); do reject H0 for = 0.01;

P -value 2 (0.025, 0.05); do not reject H0 for = 0.01;

P -value 2 (0.05, 0.1); do reject H0 for = 0.01;
none of the preceding

Solution to Q18:
This is paired test. Compute dierence (crossfertilized-selertilized). The obtained mean and standard deviation
are d = 2.606667, sD = 4.712819. The test statistics is
T0 =

D
p tn
SD / n

1.

Its observed value is 2.142152. We compute P -value as 2P (t14 > 2.142152) 2 2 (0.025, 0.05) = (0.05, 0.1). Do
not reject for = 0.01.

Q19. The thickness of a plastic film (in mils) on a substrate material is thought to be influenced by the temperature
at which the coating is applied. A completely randomized experiment is carried out. Eleven substrates are
coated at 125o F , resulting in a sample mean coating thickness of x
1 = 103.5 and a sample standard deviation of
s1 = 10.2. Another 11 substrates are coated at 150o F , for which x
2 = 99.7 and s2 = 11.7 are observed. Assume
normality. The value of the appropriate test statistics is (The numbers are rounded down to the third dp).
(a)

0.890;

(b)

(e)

None of the preceding

1.035;

(c)

1.815;

(d)

Solution to Q19:
This is two-sample test. The observed value of the test statistics
x
1
2
s1 /n1

x
2
+

s22 /n2

103.5 99.7
=p
= 0.8119597.
10.22 /11 + 11.72 /11

1.890;

Q20. For a set of 12 pairs of observations on (xi , yi ) from an experiment, the following summary for x and y is
12
12
12
12
12
X
X
X
X
X
obtained:
xi = 25,
yi = 432,
x2i = 59,
yi2 = 15648,
xi yi = 880.5. The estimated value of y at
i=1

i=1

i=1

x = 5 from the least squares regression line is:

(a)

27.78

(b)

47.77

(c)

i=1

i=1

41.87

(d)

55.97

(e)

none of the preceding

Q21. Assuming that the simple linear regression model Y = 0 + 1 x + " is appropriate from n = 14 observations
we computed the estimated regression line yb = .6649 + .83075 x. Given that Syy = 4.1289 and Sxy = 4.4094,
compute the estimated standard error for the slope.
(a)

0.3176

(b)

0.0388

(c)

0.0855

(d)

0.0073

(e)

none of the preceding

Q22. An engineer wants to study the variability of the production process. A sample of size n = 10 was taken every
= 30.2 and r/d2 = 2.5. Determine the lower and the
2 hours. After m = 25 preliminary samples, one obtains x
upper control limits for a R chart.
(a)

LCL=1.716 and UCL=13.674

(b)

LCL=4.511 and UCL=15.144

(c)

LCL=27.830 and UCL=32.570

(d)

LCL=28.696 and UCL=31.711

(e)

none of the preceding

Solution to Q22:
From table XI, with n = 10, we obtain d2 = 3.078, D3 = 0.223 and D4 = 1.777. So r = 2.5 d2 = 7.695. The
limits for R are
LCL = r D3 = (7.695)(0.223) = 1.716
et
U CL = r D4 = (7.695)(1.777) = 13.674.

Q23. A company manufactures computers. To control their quality, 50 computers are tested every day. We have the
following data for the consecutive 15 days:

Sample
# of defective

1
3

2
2

3
5

4
1

5
4

6
1

7
6

8
3

9
5

10
0

11
6

12
2

13
4

14
1

The lower and upper control limits for the proportion of defective are, respectively:
(a)

LCL =

0.0391, U CL = 0.1725

(c)

LCL = 0.0391, U CL = 0.1725

(b)

LCL = 0, U CL = 0.1725

(d)

LCL =

0.0391, U CL = 0.2599

15
7

10

(e)

None of the preceding.

Solution to Q23:
We have p = 0.67, n = 50 so that
LCL = p

p(1

p)
n

U CL = p + 3

0.0391 ! LCL = 0,

p(1

p)
n

= 0.1725

Q24. The following graphs show histogram and boxplot for two samples, A and B. Based on these graphs we may
conclude that
(a)
Only A comes from a normal population.
(b)

Only B comes from a normal population.

(c)

Both A and B come from normal populations.

15

Sample A

0 5

Frequency

Sample A

20 40 60

Sample B

Frequency

Sample B

This is the last question

11

Solutions to multiple choice questions:

Q1 ! c

Q2 ! a

Q3 ! d

Q4 ! b
Q5 ! a

Q6 ! b
Q7 ! c

Q8 ! a

Q9 ! d

Q10 ! b
Q11 ! d
Q12 ! b
Q13 ! a

Q14 ! b
Q15 ! b
Q16 ! b
Q17 ! a
Q18 ! a
Q19 ! e

Q20 ! a
Q21 ! c

Q22 ! a

Q23 ! b
Q24 ! a