1

APPLIED STATISTICS (SQQS2013)

INDIVIDUAL ASSIGNMENT 1 60 MARKS (20%)

INSTRUCTIONS:
SUBMIT ONLINE 2 WEEKS AFTER FINISH CHAPTER 2

NAME : GURUSHALINI POOBALAN

MATRIC NO: 264720

1. Determine the critical value z α that corresponds to the given level of confidence. (4M)
2

a. 92% b. 95%
α = 1-0.92 α = 1-0.95
= 0.08 = 1-α α α/2 Zα/2
0.05
α /2= 0.08/2 α /2= 0.92 0.08 0.04 1.7507
0.05/2
= 0.04 = 0.025 0.95 0.05 0.025 1.9600

c . 96% d . 99% 0.96 0.04 0.02 2.0537

α = 1-0.96 α=
1-0.99 0.99 0.01 0.005 2.5758
= 0.04 =
0.01
α /2= 0.04/2 α /2= 0.01/2
= 0.02 = 0.005

2. Determine whether the statement is true or false. If the statement is false, rewrite it as a
true statement. (5M)

a. A 95% confidence interval for a population proportion with lower bound 0.45 and
upper bound 0.51 means there is a 95% probability the population proportion is
between 0.45 and 0.51.
-False. A 95% confidence interval for a population proportion with lower bound 0.45
and upper bound 0.51 means you can be 95% certain that the population proportion is
between 0.45 and 0.51.

b. The higher the degree of confidence, the larger the sample required to give a certain
precision.
- False . The higher the degree of confidence the smaller the sample required to give
1
 2

A certain precision.

c. To determine the value of standard error of the mean, the total error is divided by the
sample size.
- False. To determine the value of standard error of the mean, the standard
deviation
Divided by the sample size.

d. If the size of a sample equals the size of the population, we would expect any error in
estimating the population parameter.
- True

e. We can expect some difference between sample statistics and the corresponding
population parameters. This difference is called the sampling error.
-True

3. Travelers pay taxes for flying, car rentals and hotels. The following data represent the
total travel tax (in RM) for a 3-day business trip in eight randomly selected cities.

67.81 78.69 68.99 84.36 80.24 86.14 101.27 99.29

a. Determine a point estimate for the population mean travel tax. (1M)

x
x   

 n 
= 67.81 + 78.69 + 68.99 + 84.36 + 80.24 + 86.14 + 101.27 + 99.29
8
= 669.79
8
= 83.35

b. Determine a point estimate for the population variance travel tax.(1M)

 2

x 2
 nx2
n 1

(67.81 - 83.35) 2  (78.69  83.35) 2  (68.99  83.35) 2  (84.36  83.35) 2 

(80.24  83.35) 2  (86.14  83.35) 2  (101.27  83.35) 2 (99.29  83.35) 2
=
8-1
= 1063.1031
7
= 151.87

2
 3

c. Construct and interpret a 99% confidence interval to estimate the mean tax paid for a
3-day business trip.(3M)

n= 8 , df = n-1
= 8-1 =7

  151.87 α = 1- 0.99
= 12.3236 = 0.01

α = 0.005
2

t
2 = 3.4995
  
t , n  1 
x + 2  n
 12.3236 
 
= 83.35 + 3.4995  8 
= (98.5975,68.1025)
= 98.60 < µ <68.10

We are 99% confident that the mean tax paid for three-day business trip is between
68.1025 and 98.5975

4. A researcher wishes to see if there a difference in the cholesterol levels of two groups of
men. A random sample of 30 men between the ages of 25 and 40 is selected and tested.
The average level is 223 with the standard deviation is 6. A second sample of 42 men
between the ages of 41 and 56 is selected and tested. The average of this group is 229
with the standard deviation is 8. Assume that both variables are approximately normally
distributed.
a. What is the point estimate of the mean differences of the cholesterol levels? (1M)

x1  223 x 2  229

x1  x 2
= 223 - 229

3
 4

=-6

b. Find the 95% confidence interval for the difference of the two means. (3M)

n1  30 n2  42 x1  223 x 2  229 s1  6 s2  8

α = 1-0.95
=0.05


Z  1.9600
α = 0.025 2
2

  s12 s22 
( x1  x 2 )  Z 
2  n1 n2 
 6 2 82 
  
 30 42 
= (223-229) + (1.96)  
= -6 + (1.96)(1.65)

= (-9.234 , -2.766)

= The 95% confidence interval for the two mean difference between the mean
is
-9.234 < 1   2 < -2.766

c. Based on answer in (a), is there a difference in the cholesterol levels between the two
groups at 5% significance level? Justify your answer. (2M)

Hypothesis:
H0: µ1 - µ2 = 0 or µ1 = µ2
H1: µ1 ≠ µ2

Test statistic:

x́1 −x́2
−6
Z= s1 s 2 =
√ +
2

n1 n2
= -3.6357
2
1.6503

4
 5

Decision rule: reject H0 if z ≤ -1.96

Therefore we reject null hypothesis because -3.6357 < -1.96
Hence there is a difference in the cholesterol level between the two groups at 5%
significant level.

5. A mechanical engineer in a car manufacturing company is investigating two types of

bumper guards. Random sample of 6 guards from each type were mounted on a compact
car. Each car was then run into a concrete wall at 8km per hour. The following are the
costs of repairs (in RM):

Bumper guard 1 305 420 363 485 300 360

Bumper guard 2 405 345 336 450 400 360

Assume that the costs of repairs for two types of bumper guards are approximately
normally distributed.
a. What is the point estimate of the mean and standard deviation of cost of repair for
bumper guard 1? (1M)

x1 
x
n1

= 305 + 420 + 363 + 485 + 300 + 360

6

= 372.1667

s1 
x 2
 nx2
n 1

(305  372.1667) 2  (420  372.1667) 2  (363  372.1667) 2 

(485  372.1667) 2  (300  372.1667) 2  (360  372.1667) 2
=

6-1

= 70.6694

b. What is the point estimate of the mean differences of cost of repairs? (1M)

5
 6

x2 
x
n2
= 405 + 345 + 336 + 450 + 400 + 360
6
= 382.6667

x 2  x1
= 382.6667 - 372.1667
= 10.5

c. Assuming that the variances of cost of repairs are unequal, construct a 99%
confidence interval on the mean differences of cost of repairs. (3M)

n1  6
n2  6 x1  372.1667 x 2  382.6667 s1  70.6694

s2 
x 2
 nx2
n 1

(405  382.6667) 2  (345  382.6667) 2  (336  382.6667) 2 

(450  382.6667) 2  (400  382.6667) 2  (360  382.6667) 2
=
6-1

= 43.4588

i) The degrees of freedom

Assuming that the variances are unequal, the degrees of freedom are given by

s1 2 s2 2

( + )2
n1 n2
=
1 s1 2 1
2 s2 2 2

( ) + ( )
n1−1 n 1 n2−1 n2

70.66942 43.45882
= ( + )
6 6

1 70.66942 2 1 43.45882 2
( ) + ( )
6−1 6 6−1 6

6
 7

= 8.3086 @ 8

Based on the information, the significance level is α= (1−0.99) / 2 = 0.005, and the
degree of freedom is 8. Therefore the critical value:

t α = 3.355
2
ii) Standard error:
s s
√ 2

SE = 1 + 2
n1 n2
2
2

2
= 70.6694 + 43.4588
√ 6
= 33.8694
6

The 99% Confidence interval is computed as:

s s
√
CI = ( x́ 1 − x́ 2) ± t α 1 + 2
2
2 2

n1 n2

= (372.1667 – 382.6667) – 3.355(33.8694), (372.1667 – 382.6667) +

3.355(33.8694)

= -124.1451, 103.1451

Therefore, we are 99% confident that the true difference between cost of repair means
is contained by the interval (-124.1451, 103.1451).

d. Based on the confidence interval obtained in (c), can you conclude that there is
difference between average costs of repairs for two types of bumper guards? Give
your reason. (2M)

Based on the 99% confidence interval of true difference between population means
(-124.1451, 103.1451). There is insufficient evidence to conclude that there is difference
between average costs of repairs between the two types of bumper cars, since the 99%
confidence interval for difference in population mean of two types of bumper contains
0.

6. The manufacturer of the ColourSmart television claims that 85% of its sets last at least
five years without needing a single repair. In order to test this claim, a consumer group
randomly selected 400 consumers who have owned a ColourSmart television set for five
years. Of these 400 consumers, 65 say that their ColourSmart television sets did need at
least one repair.

7
 8

a. Obtain the point estimate for the proportion of all ColourSmart television sets that
have lasted at least five years without needing a single repair. (1M)

Let p = denotes the population proportion

Let ^p = denotes the sample proportion and n denotes the sample size

65
The point estimate for the proportion is ^p =
400
= 0.1625

b. Determine whether the condition is satisfied to use the large sample formula (2M)
^p q^
^p ± Z α
2 √
n

p^ q^
^p ± Z α
2 √
n
In order to use the large sample formula, the np and n(1-p) must be at least 10.
n = 400, p = 85%
np = 400×85% = 340>10
n(1-p) = 400(1− 0.85) = 60>10
So, the condition is satisfied to use the large sample formula.

c. Find a 99% confidence interval for the true proportion of all ColourSmart television
sets that have lasted at least five years without needing a single repair. (3M)
65
=0.1625 , n = 400, SE = 0.163×(1−0.163) = 0.01844, α/2=(1−0.99)/2 =
^p =
0.005
400 √ 400

At 99% confidence interval, margin of error is:

^p ×(1−q^ ) Z α
ME =
√ n
×
2

0.163×(1−0.163)
=
√ 400
= 0.01844 × 2.5758
× Z0.005

= 0.0475

A 99% confidence level for the true proportion p is:

8
 9

^p ×(1−q^ ) Z α
CI = ^p ±
√ n
×
2

= (0.1625 − 0.0475, 0.1625 + 0.0475)

= (0.0115, 0.210)

7. A researcher wishes to see if the average length of the major rivers in the United States is
the same as the average length of the major rivers in Europe. The data in miles of a
sample of rivers are shown below. At  = 0.01, is there enough evidence to reject the
claim? (7M)

United States Europe

729 560 434 481 724 820
329 332 360 532 357 505
450 2315 865 1776 1122 496
330 410 1036 1224 634 230
329 800 447 1420 326 626
600 1310 652 877 580 210
1243 605 360 447 567 252
525 926 722 824 932 600
850 310 430 634 1124 1575
532 375 1979 565 405 2290
710 545 259 675 454
300 470 425

From the given data, we need to find at  = 0.01, is there enough evidence to reject the claim.

For United State:

Sample 1,n = 36

x́ 1 = (729+560+434+329+332+360+450+2315+865+330+410+1036+329+800+447+6
00+1310+652+1243+605+360+525+926+722+850+310+430+532+375+1979+
710+545+259+300+470+425)

36
= 662.6111

9
 10

2
S12 = Σ(xi - x̄)
N-1
= 7083416.5555556
36-1

S1 = √ 202383.33015873
= 449.8703

For Europe,
Sample 2, n = 32

x2 = (481+724+820+532+357+505+1776+1122+496+1224+634+230+1420+326+626
+877+580+210+447+567+252+824+932+600+634+1124+1575+565+405+2290
+675+454)

32
= 758.875

S22 = Σ(xi - x̄)2

N-1
= 6968653.5
32-1

S2 = √ 224795.27419355

= 474.1258

 = 0.01
Z 0.01 = 2.576
2
Hence, {Zα/2: Z > 2.576}
Hypothesis:
H0: µ1 - µ2 = 0 or µ1 = µ2 (Claim)
H1: µ1 ≠ µ2

10
 11

Test statistic:

x́1 −x́2 662.611-758.875

Z= s1 s 2 = 449.8703 2 474.12582
√ 2

+
n1 n2
2

√ 36
+
32

= − 0.856

Hence, Z = -0.856 ≤ Zα/2 = 2.576

So, concluded that null hypothesis is not rejected. There is not enough evidence to
reject the claim that the average lengths of the rivers are the same

8. The following null and alternative hypotheses have been stated:

H 0: μ1−μ 2 = 0
H A : μ1−μ 2 ≠ 0
To test the null hypothesis, random samples have been selected from the two normally
distributed populations with equal variance. The following sample data were
observed:
Sample from population 1 Sample from population 2

33 29 35 39 39 41 25 33 38 46 43 42 46 44 47 50 43 39

Test the null hypothesis using an alpha level equal to 0.05. (7M)

Given that:
H 0: μ1−μ 2 = 0
H A : μ1−μ 2 ≠ 0
33 + 29 +35 + 39 + 41 + 25 + 33 +38
x́ 1 = 9
= 312
9
= 34.6667

S12 = Σ(xi - x̄)2

N-1

11
 12

= 220
9-1

s1 = √ 27.5

= 5.2440442408508

x́ 2 = 46 + 43 + 42 + 46 + 44 + 47+ 50 + 43 +39

9
= 400
9
= 44.4444

S22 = Σ(xi - x̄)2

N-1

= 82.22
9-1

s2 = √ 10.277777777778
= 3.2058973436119

Pooled Variance
( n1−1 ) s1 + ( n2 −1 ) s 2
2 2

Sp2 =
n1 +n 2−2
( 8 ) 5.24402+ ( 8 ) 3.2058 2
=
16
= 18.8883
Test statistic:
x́ 1−x́ 2
t= sp sp
√ 2

+
n1 n2
2

34.6667-44.4444
= 18.8883 18.8883
√9
+
9

= -4.769

Decision rules: Reject H0 if t ≥ t α

2

At alpha = 0.05, t 0.05 = 2.120

2

Decision: Since the test statistic value is less than the lower critical value (-4.77 ≤
- 2.120), so we should reject the null hypothesis.

12
 13

Interpretation: There is sufficient evidence to reject the H0 at alpha 0.05. It may be

conclude that that the population mean for sample 1 is difference from

population mean for sample 2 at alpha 0.05.

9. Given the following null and alternative hypotheses, conduct a hypothesis test using an
alpha equal to 0.05. (Note: The population standard deviations are assumed to be known.)

H 0 : μ1 ≤ μ2
H 0 : μ1> μ2
The sample means for the two populations are shown as follows:
n1 = 40 x́ 1 = 144 σ 1 = 11
n2 = 50 x́ 2 = 129 σ 2 = 16 (6M)

Null and alternative hypotheses

The following null and alternative hypotheses need to be tested:
H 0 : μ1 ≤ μ2
H 0 : μ1> μ2
This corresponds to a right-tailed test, for which a t-test for two population means,
with two independent samples, with unknown population standard deviations will be
used.
Hence, it is found that the critical value for this right-tailed test is tc = 1.662, for α =
0.05 and df = 40 + 50 -2 = 88
The rejection region for this right-tailed test is R= {t: t > 1.662}
Test statistic:
Since it is assumed that the population variances are equal, the test statistic is
computed as follow:
Pooled variance

( n1−1 ) s1 + ( n2 −1 ) s 2
2 2

Sp2 =
n1 +n 2−2

( 39 ) 11 2+ ( 49 ) 162
=
88

= 196.1704

x́ 1−x́ 2
t= sp sp
√ +
n1 n2
144 - 129
2 2

= 196.1704 196.1704
√ 40
+
50

= 5.049

13
 14

Decision: Since it is observed that t = 5.049 > tc = 1.662, then concluded that the null
hypothesis is rejected.

Conclusion: It is concluded that the null hypothesis H0 is rejected. Therefore, there is

enough evidence to claim that population mean μ1is greater than μ2, at
the 0.05 significant level.

10. A researcher wishes to test the claim that on average more juveniles than adults are
classified as missing persons. Records for the last five years are shown and the results are
given in the output. At  = 0.10 is there enough evidence to support the claim? (7M)

Juveniles 65,513 65,934 64,213 61,954 59,167

Adults 31,364 34,478 36,937 35,946 38,209
Group Statistics

Std. Error
PERSON N Mean Std. Deviation Mean
NUMBER Juv 5 63356.20 2808.31385 1255.916
Adults 5 35386.80 2631.03947 1176.637

14
 15

Independent Samples Test

Levene's Test for

Equality of Variances t-test for Equality of Means
90% Confidence
Interval of the
Mean Std. Error Difference
F Sig. t df Sig. (2-tailed) Difference Difference Lower Upper
NUMBER Equal variances
.094 .767 16.252 8 .000 27969.400 1720.9878 24769.14 31169.66
assumed
Equal variances
16.252 7.966 .000 27969.400 1720.9878 24767.38 31171.42
not assumed

The null and alternative hypothesis are: H 0 : μ1 ≤ μ2 vs H 1 : μ1> μ2

Given that:

x́ 1 = 65513 +65934 + 64213 +61954 + 59167

5
= 316781
5

= 63356.2

S12 = Σ(xi - x̄)2

N-1
= 31546506.8
5-1

s1 = √ 7886626.7

= 2808.3138535427

2808.31385
SE1 = = 1255.9161357352
√5

x́ 2 = 31364 + 34478 + 36937 + 35946 +38209

5
= 176934
5
= 35386.8

S22 = Σ(xi - x̄)2

N-1
15
 16

= 27689474.8
5-1

s2 = √ 6922368.7

= 2631.0394713877

2613.03947
SE2 = = 1176.6366219016
√5
To find the critical value, since the test is two-tailed, α = 0.10, the variance are
unequal and the degree of the freedom (df) is 5-1=4

from the table t cv = 2.1318

Test statistic:
x́1 −x́2
t= s1 s 2
√ 2

+
n1 n2
2

63356.2 - 35386.8
= 2808.313852 2613.039472
√ +
5 5

= 16.2519

Since it is observed that t = 16.2519 > tcv = 2.1318, then concluded that the null
hypothesis is rejected.There is enough evidence to support the claim that, on average,
more juveniles that adults are classified as missing person.

16