ASSIGNMENT 2

6.23
n=10 ; π =0.2
10
n! x n−x 10 ! 0
(a) P ( X=0 )= × π ×(1−π ) = × 0.2 × 0.8 ≈ 0,1074
x ! ( x−n ) ! 0 ! ( 10−0 ) !
(b)

( )
9
10 !
P ( X ≥2 )=1−P ( X <2 )=1−[ P ( X=0 ) + P ( X=1 ) ] =1− 0.1074+
1
× 0.2 × 0.8 ≈ 0.6242
(
1 ! 10−1 !)
(c)
9 8
10 ! 1 10! 2
P ( X <3 )=P ( X ≤ 2 )=P ( X=0 ) + P ( X =1 ) + P ( X=2 ) =0.1074+ × 0.2 × 0.8 + × 0.2 × 0.8 ≈ 0
1 ! ( 10−1 ) ! 2! ( 10−2 ) !
(d) E( X )=n × π=10 × 0.2=2
(e) SD(X )=√ nπ ( 1−π ) =√ 10 × 0.2× 0.8 ≈ 1.2650
(f)

X = Number of credit card payments P(X)

0 0.1074
1 0.2684
2 0.3020
3 0.2013
4 0.0881
5 0.0264
6 0.0055
7 0.0008
−3
8 0.0737 × 10
−3
9 0.0041 ×10
−3
10 0.0001 ×10
(g)The data in the graph is right-skewed (Binominal Distribution and π < 0.5)
6.37
λ=1 ,7
0 −1.7
1.7 × e
(a) P ( X ≥1 )=1−P ( X <1 ) =1−P ( X=0 )=1− ≈ 0.8173
0!
x −λ 0 −1.7
λ ×e 1.7 × e
(b) P ( X=0 )= = ≈ 0.1827
x! 0!
(c)
1 −1.7 2 −1.7 3
1.7 × e 1.7 × e 1.7 ×
P ( X ≥ 4 )=1−P ( X < 4 )=1−[P ( X =1 ) + P ( X=2 ) + P ( X =3 ) + P ( X=4 ) ]=1−(0.183+ + +
1! 2! 3
(d)

X = Number of errors P(X)

0 0.1827
1 0.3106
2 0.2640
3 0.1496
4 0.0636
5 0.0216
6 0.0061
7 0.0015
8 0.0003

Because this is a Poisson Distribution  PDF Table is always right-skewed.

6.92
'
n=2 500 ; π=0.001 → λ=n× π=2.5( n ≥20 ; π <0.05 → Poisson approximation )
x −λ 0 −2.5
λ ×e 2.5 × e
(a) P ( X=0 )= = =0.0821
x! 0!
(b)

( )=0.4563
1 −2.5 2 −2.5
2.5 × e 2.5 ×e
P ( X ≥3 )=1−P ( X ≤ 2 )=1−[ P ( X=0 )+ P ( X =1 ) + P ( X=2 )]=1− 0.0821+ +
1! 2!
(c) E ( X )=n × π=2' 500 ×0.001=2.5
7.38
μ=600; σ=100

(a) P ( X > x )=0.05 → P ( X−μ

σ
>
x−600
100 )=0.05 → P (Z <
100 )
x−600
=0.95 ( I )

P ( Z <1.645 )=0.95( II )
( I )∧( II ) → x=600+ 1.645× 100=764.5 . The credit score of 764.5 defines the 5% upper limit.

(b) P ( X > x )=0.75 → P (

X−μ x−600
σ
>
100 )
=0.75 → P Z < ( x−600
100 )
=0.25 ( I )

P ( Z ←0.674 )=0.25 (II )

( I )∧( II ) → x=600+ (−0,674 ) ×100=532.6  75% of the customers will have the credit score
over 532.6.

(c) P ( x 1< X < x 2 )=0.8 → P ( x −600

1
100
<
X −μ x −600
σ
< 2
100 )=0.8 → P (
x −600
1
100
<Z<
100 )
x −600
2
=0.8 ( I )

P (−1.2816< Z< 1.2816 )=0.8(II )

x=600+ (−1.2816 ) ×100=471.84
x=600+1.2816 × 100=728.16
The middle 80% of credit scores lies between 471.84 and 728.16.
7.59
λ=4.2 orders /hour → λ=0.07 orders/minute
(a) e− λx =0.5
−ln ( 0.5 )
x= ≈ 9.9 ( minutes )
0.07
(b)e− λx =0.25
−ln ( 0.25 )
x= ≈19.8 (minutes)
0.07
(c) e− λx =0.1
−ln ( 0.1 )
x= ≈ 32.89 (minutes)
0.07
8.3
μ=4.035 ; σ =0.005 ; n=25
(a) Expected range=μ ± 1.96 σ =4.035 ± 1.96 ×0.005=(4.0252 , 4.0448)
σ 0.005
(b) 95 % of the sample means=μ ±1.96 =4.035± 1.96 × =( 4.033 , 4.037 )
√n √ 25
(c) In both cases, the sample means are outside the range because both the confidence intervals
does not contain 4.02 nor 4.055.
8.17
x=0.2731 ; σ =0.000959 ; n=58
σ 0.000959
99 % CI =x ± z α /2 =0.2731 ± 2.576 × =(0.27278 ; 0.27342)
√n √ 58
8.23
x=45.66 ; σ=27.29; n=21
sx 27.79
(a) 95 % CI=x ±t 1− α ;n−1 =45.66 ± 2.086 × =( 33.01 ;58.31 )
( 2 ) √n √ 21
(b) To narrow the confidence interval, we need to increase the value of n (sample size).
9.17
x=3.59 ; μ=3.5 ; σ=0.18 ; n=25
(a)Null hypothesis: H 0 : μ ≤3.5
Alternative hypothesis: H 1 : μ >3.5
x−μ 3.59−3.5
z= = =2.5
(b) σ 1.8
√n √25
(c) α =0.1 → z α=2.33
Reject H 0 if z >2.33 ( 2.5> 2.33 ) → Reject thenull hypothesisat 1% level of significance
The sample exceeds the manufacture’s claim.
(d) p−value=P ( Z> z )=P ( Z >2.5 ) =1−P ( Z ≤2.5 )=1−NORM . DIST ( 2.5 )=1−0.9938=0.0062
9.38
x=17.78 ; μ=18 ; s=0.41 ; n=18
(a)Null hypothesis: H 0 : μ ≥18
Alternative hypothesis: H 1 : μ <18
x−μ 17.78−18
t= = =−2.277
s 0.41
√n √18
  There is enough evidence to conclude that at 5% level of significance, the true mean is
smaller than the specification.
(b)The conclusion is sensitive to the choice of level of significance.
(c) df =n−1=18−1=17
p−value=T . DIST (|t| , df ,tails )=TDIST ( 2.277 ,17 ,1 ) =0.018

The p – value is less than the level of significance (0.018 < 0.05)  There is enough evidence
to reject the null hypothesis.
10.8
x 1=170.3333 ; s 1=5.0332 ; n1=12

x 2=161.0833 ; s 2=5.5671 ; n2=12

H 0 : μ1−μ2 ≤0

H 1 : μ 1−μ2 >0

df =n1 +n2−2=12+12−2=22

2 ( n 1−1 ) s 12 + ( n2−1 ) s 22 ( 12−1 ) ×5.03322 + ( 12−1 ) × 5.56712

sp = = =28.1629
n1+ n2−2 12+12−2

x 1−x 2 170.3333−161.0833
t= = =4.27

√ √
2 2 2 2
sp sp 28.1629 28.1629
+ +
n1 n2 12 12

p−value=P ( t >4.27 )=T . DIST . RT ( 4.27 )=0.0002

The test statistics falls in the right-tail rejection region  Reject H 0 in favor of H 1 The mean
temperature of Panera’s coffee is higher at the 1% level of significance.
The p – value approach  Reject the H 0 because p – value < α (0.0002 < 0.1).
10.19
H 0 : μ=0

H1: μ ≠ 0

Entry failures Exit failures

Mean 50.125 53.125
Variance 40.125 29.2679
Observation 8 8
Pearson Correlation 0
Hypothesized Mean 0.654
Difference
 Degree of freedom 7
t Stat -1.712
P ( T ≤ t ) one tail 0.065
t Critical one tail 2.988
P ( T ≤ t ) two tails 0.131
t Critical two tails 3.4995

The value of the test statistic is -1.712 (does not lie in the reject region)  Fail to reject the null
hypothesis  Insufficient sample evidence to conclude a significant difference between entry
and exit failures.
10.39
2 2
H 0 :σ new =σ old
2 2
H 1 : σ new <σ old
df =n−1=12−1=11; α =0.05
F L =F . INV ( 0.05; 11; 11 )=0.3549

Reject H 0if F< 0.3549

x new =0.5002 ; s new =0.001807 ; nnew =12

x old =0.5 ; sold =0.005642; nold =12

2 2
s new 0.001807
F= 2
= 2
=0.1026
sold 0.005642

0.1026 < 0.3549  F falls into rejected region  At the 5% level of significance, we reject H 0
in favor of alternative hypothesis  The new process has a smaller variance.