CH 03

Chapter 3 Exercise Solutions
3.1.
(a)
n
x = ∑ xi n = (16.05 + 16.03 + L + 16.07 )12 = 16.029 oz
i =1
(b)
( )n =
n n 2
2
∑ xi − ∑ xi (16.052 + L + 16.07 2 ) − (16.05 + L + 16.07) 2 12
i =1 i =1
s= = 0.0202 oz
n −1 12 − 1
MTB > Stat > Basic Statistics > Display Descriptive Statistics
Descriptive Statistics: Ex3.1
Variable N N* Mean SE Mean StDev Minimum Q1 Median Q3
Ex3-1 12 0 16.029 0.00583 0.0202 16.000 16.013 16.025 16.048
Variable Maximum
Ex3-1 16.070
3.2.
(a)
n
x = ∑ xi n = (50.001 + 49.998 + L + 50.004 )8 = 50.002 mm
i =1
(b)
( )n =
n n 2
2
∑ xi − ∑ xi (50.0012 + L + 50.0042 ) − (50.001 + L + 50.004) 2 8
i =1 i =1
s= = 0.003 mm
n −1 8 −1
Ex3-2 8 0 50.002 0.00122 0.00344 49.996 49.999 50.003 50.005
Variable Maximum
Ex3-2 50.006
3-1
3.3.
(a)
n
x = ∑ xi n = (953 + 955 + L + 959 )9 = 952.9 °F
i =1
(b)
( )n =
n n 2
2
∑ x − ∑ xi
i
(9532 + L + 9592 ) − (953 + L + 959) 2 9
i =1 i =1
s= = 3.7 °F
n −1 9 −1
Ex3-3 9 0 952.89 1.24 3.72 948.00 949.50 953.00 956.00
Variable Maximum
Ex3-3 959.00
3.4.
(a)
In ranked order, the data are {948, 949, 950, 951, 953, 954, 955, 957, 959}. The sample
median is the middle value.
(b)
Since the median is the value dividing the ranked sample observations in half, it remains
the same regardless of the size of the largest measurement.
3.5.
Ex3-5 8 0 121.25 8.00 22.63 96.00 102.50 117.00 144.50
Variable Maximum
Ex3-5 156.00
3-2
3.6.
(a), (d)
Ex3-6 40 0 129.98 1.41 8.91 118.00 124.00 128.00 135.25
Variable Maximum
Ex3-6 160.00
(b)
Use n = 40  7 bins
MTB > Graph > Histogram > Simple
(c)
MTB > Graph > Stem-and-Leaf
Stem-and-Leaf Display: Ex3.6
Stem-and-leaf of Ex3.6 N = 40
Leaf Unit = 1.0
2 11 89
5 12 011
8 12 233
17 12 444455555
19 12 67
(5) 12 88999
16 13 0111
12 13 33
10 13
10 13 677
7 13
7 14 001
4 14 22
HI 151, 160
3-3
3.7.
Use n = 90 ≅9 bins
3-4
3.8.
(a)
Stem-and-Leaf Plot
2 12o|68
6 13*|3134
12 13o|776978
28 14*|3133101332423404
(15) 14o|585669589889695
37 15*|3324223422112232
21 15o|568987666
12 16*|144011
6 16o|85996
1 17*|0
Stem Freq|Leaf
(b)
Use n = 80 ≅9 bins
Note that the histogram has 10 bins. The number of bins can be changed by editing the
X scale. However, if 9 bins are specified, MINITAB generates an 8-bin histogram.
Constructing a 9-bin histogram requires manual specification of the bin cut points.
Recall that this formula is an approximation, and therefore either 8 or 10 bins should
suffice for assessing the distribution of the data.
3-5
3.8(c) continued
MTB > %hbins 12.5 17 .5 c7

Row Intervals Frequencies Percents
1 12.25 to 12.75 1 1.25
2 12.75 to 13.25 2 2.50
3 13.25 to 13.75 7 8.75
4 13.75 to 14.25 9 11.25
5 14.25 to 14.75 16 20.00
6 14.75 to 15.25 18 22.50
7 15.25 to 15.75 12 15.00
8 15.75 to 16.25 7 8.75
9 16.25 to 16.75 4 5.00
10 16.75 to 17.25 4 5.00
11 Totals 80 100.00
(d)
Leaf Unit = 0.10
2 12 68
6 13 1334
12 13 677789
28 14 0011122333333444
(15) 14 555566688889999
37 15 1122222222333344
21 15 566667889
12 16 011144
6 16 56899
1 17 0
median observation rank is (0.5)(80) + 0.5 = 40.5

x0.50 = (14.9 + 14.9)/2 = 14.9
Q1 observation rank is (0.25)(80) + 0.5 = 20.5

Q1 = (14.3 + 14.3)/2 = 14.3
Q3 observation rank is (0.75)(80) + 0.5 = 60.5

Q3 = (15.6 + 15.5)/2 = 15.55
(d)
10th percentile observation rank = (0.10)(80) + 0.5 = 8.5
x0.10 = (13.7 + 13.7)/2 = 13.7
90th percentile observation rank is (0.90)(80) + 0.5 = 72.5

x0.90 = (16.4 + 16.1)/2 = 16.25
3-6
3.9.
MTB > Graph > Probability Plot > Single
When plotted on a normal probability plot, the data points tend to fall along a straight
line, indicating that a normal distribution adequately describes the volume of detergent.
3.10.
3-7
When plotted on a normal probability plot, the data points tend to fall along a straight
line, indicating that a normal distribution adequately describes the furnace temperatures.
3-8
3.11.
When plotted on a normal probability plot, the data points do not fall along a straight line,
indicating that the normal distribution does not reasonably describe the failure times.
3.12.
When plotted on a normal probability plot, the data points do not fall along a straight line,
indicating that the normal distribution does not reasonably describe process yield.
3-9
3.13.
(In the dialog box, select Distribution to choose the distributions)
3-10
3.13 continued
Both the normal and lognormal distributions appear to be reasonable models for the data;
the plot points tend to fall along a straight line, with no bends or curves. However, the
plot points on the Weibull probability plot are not straight—particularly in the tails—
indicating it is not a reasonable model.
3-11
3.14.
3-12
3.14 continued
Plotted points do not tend to fall on a straight line on any of the probability plots, though
the Weibull distribution appears to best fit the data in the tails.
3-13
3.15.
3-14
3.15 continued
The lognormal distribution appears to be a reasonable model for the concentration data.
Plotted points on the normal and Weibull probability plots tend to fall off a straight line.
3-15
3.16.
MTB > Graph > Time Series Plot > Single (or Stat > Time Series > Time Series Plot)
From visual examination, there are no trends, shifts or obvious patterns in the data,
indicating that time is not an important source of variability.
3.17.
3-16
Time may be an important source of variability, as evidenced by potentially cyclic

behavior.
3-17
3.18.
Although most of the readings are between 0 and 20, there are two unusually large
readings (9, 35), as well as occasional “spikes” around 20. The order in which the data
were collected may be an important source of variability.
3.19.
Ex3.7 90 0 89.476 0.438 4.158 82.600 86.100 89.250 93.125
Variable Maximum
Ex3.7 98.000
3-18
3.20.
Leaf Unit = 0.10
2 82 69
6 83 0167
14 84 01112569
20 85 011144
30 86 1114444667
38 87 33335667
43 88 22368
(6) 89 114667
41 90 0011345666
31 91 1247
27 92 144
24 93 11227
19 94 11133467
11 95 1236
7 96 1348
3 97 38
1 98 0
Neither the stem-and-leaf plot nor the frequency histogram reveals much about an
underlying distribution or a central tendency in the data. The data appear to be fairly well
scattered. The stem-and-leaf plot suggests that certain values may occur more frequently
than others; for example, those ending in 1, 4, 6, and 7.
3.21.
MTB > Graph > Boxplot > Simple
3-19
3.22.
MTB > Graph > Boxplot > Simple
3.23.
x: {the sum of two up dice faces}
sample space: {2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12}
Pr{x = 2} = Pr{1,1} = 1 × 1 = 1
6 6 36
(
6 6 )( )
Pr{x = 3} = Pr{1, 2} + Pr{2,1} = 1 × 1 + 1 × 1 = 2
6 6 36
( )(
6 6 6 6 6 6 )(
Pr{x = 4} = Pr{1,3} + Pr{2, 2} + Pr{3,1} = 1 × 1 + 1 × 1 + 1 × 1 = 3
36 )
...
⎧1/ 36; x = 2 2 / 36; x = 3 3 / 36; x = 4 4 / 36; x = 5 5 / 36; x = 6 6 / 36; x = 7

p ( x) = ⎨
⎩5 / 36; x = 8 4 / 36; x = 9 3 / 36; x = 10 2 / 36; x = 11 1/ 36; x = 12 0; otherwise
3.24.
11
x = ∑ xi p( xi ) = 2 (1 36 )+ 3 (2 36 )+ L + 12 (1 36 )= 7
i =1
2
∑ xi p ( xi ) −⎡⎢∑ xi p ( xi ) ⎤⎥ n
n n
i =1 ⎣i =1 ⎦ 5.92 −7 2 11
S= = = 0.38
n −1 10
3-20
3.25.
This is a Poisson distribution with parameter  = 0.02, x ~ POI(0.02).
(a)
e −0.02 (0.02)1
Pr{x = 1} = p(1) = = 0.0196
1!
(b)
e −0.02 (0.02)0
Pr{x ≥1} = 1 −Pr{x = 0} = 1 − p (0) = 1 − = 1 −0.9802 = 0.0198
0!
(c)
This is a Poisson distribution with parameter  = 0.01, x ~ POI(0.01).
e −0.01 (0.01)0
Pr{x ≥1} = 1 −Pr{x = 0} = 1 − p (0) = 1 − = 1 −0.9900 = 0.0100
0!
Cutting the rate at which defects occur reduces the probability of one or more defects by
approximately one-half, from 0.0198 to 0.0100.
3.26.
+∞
For f(x) to be a probability distribution, ∫ f ( x)dx must equal unity.
−∞
∞
∫ke dx = [−ke ]0 = −k [0 −1] = k ⇒ 1
−x −x ∞
This is an exponential distribution with parameter =1.

 = 1/ = 1 (Eqn. 3.32)
2 = 1/2 = 1 (Eqn. 3.33)
3.27.
⎧(1 + 3k ) / 3; x = 1 (1 + 2k ) / 3; x = 2
p ( x) = ⎨
⎩(0.5 + 5k ) / 3; x = 3 0; otherwise
(a)
∞
To solve for k, use F ( x) = ∑ p ( xi ) = 1
i =1
(1 + 3k ) + (1 + 2k ) + (0.5 + 5k )
=1
3
10k =0.5
k =0.05
3-21
3.27 continued
(b)
3 ⎡1 + 3(0.05) ⎤ ⎡1 + 2(0.05) ⎤ ⎡0.5 + 5(0.05) ⎤
μ = ∑ xi p( xi ) = 1× ⎢ ⎥ + 2×⎢ ⎥ + 3× ⎢ ⎥⎦ = 1.867
i =1 ⎣ 3 ⎦ ⎣ 3 ⎦ ⎣ 3
3
σ 2 = ∑ xi2 p( xi ) −μ 2 = 12 (0.383) + 22 (0.367) + 32 (0.250) −1.867 2 = 0.615
i =1
(c)
⎧ 1.15
⎪ =0.383; x =1
3
⎪
⎪ 1.15 + 1.1
F ( x) =⎨ =0.750; x =2
⎪ 3
⎪1.15 + 1.1 + 0.75
⎪ =1.000; x =3
⎩ 3
3.28.
p( x) = kr x ; 0 < r < 1; x = 0,1, 2,K

∞
F ( x) = ∑ kr x = 1 by definition
i =0
k ⎡⎣1 (1 − r )⎤⎦ = 1
k =1− r
3.29.
(a)
This is an exponential distribution with parameter  = 0.125:
Pr{x ≤1} = F (1) = 1 −e −0.125(1) = 0.118
Approximately 11.8% will fail during the first year.
(b)
Mfg. cost = $50/calculator
Sale profit = $25/calculator
Net profit = $[-50(1 + 0.118) + 75]/calculator = $19.10/calculator.
The effect of warranty replacements is to decrease profit by $5.90/calculator.
3-22
3.30.
12 12 12
4 x2 12
Pr{x < 12} = F (12) = ∫f ( x)dx = ∫ 4( x −11.75)dx = −47 x 11.75 = 11.875 −11.75 = 0.125
−∞ 11.75
2 11.75
3.31.
This is a binomial distribution with parameter p = 0.01 and n = 25. The process is
stopped if x  1.
⎛25 ⎞
Pr{x ≥1} = 1 −Pr{x < 1} = 1 −Pr{x = 0} = 1 −⎜ ⎟(0.01)0 (1 −0.01) 25 = 1 −0.78 = 0.22
⎝0 ⎠
This decision rule means that 22% of the samples will have one or more nonconforming
units, and the process will be stopped to look for a cause. This is a somewhat difficult
operating situation.
This exercise may also be solved using Excel or MINITAB:

(1) Excel Function BINOMDIST(x, n, p, TRUE)
(2) MTB > Calc > Probability Distributions > Binomial
Cumulative Distribution Function
Binomial with n = 25 and p = 0.01
x P( X <= x )
0 0.777821
3.32.
x ~ BIN(25, 0.04) Stop process if x  1.
⎛25 ⎞
Pr{x ≥1} = 1 −Pr{x < 1} = 1 −Pr{x = 0} = 1 −⎜ ⎟(0.04)0 (1 −0.04) 25 = 1 −0.36 = 0.64
⎝0 ⎠
3.33.
This is a binomial distribution with parameter p = 0.02 and n = 50.
4
⎛50 ⎞
Pr{ pˆ ≤0.04} =Pr{x ≤2} =∑⎜ ⎟(0.02) x (1 −0.02)(50−x )
x =0 ⎝ x ⎠
⎛50 ⎞ ⎛50 ⎞ ⎛50 ⎞

=⎜ ⎟(0.02)0 (1 −0.02)50 + ⎜ ⎟(0.02)1 (1 −0.02) 49 + L + ⎜ ⎟(0.02) 4 (1 −0.02) 46 =0.921
⎝0 ⎠ ⎝1 ⎠ ⎝4 ⎠
3-23
3.34.
This is a binomial distribution with parameter p = 0.01 and n = 100.
σ = 0.01(1 −0.01) 100 = 0.0100
Pr{ pˆ > kσ + p} = 1 −Pr{ pˆ ≤kσ + p} = 1 −Pr{x ≤n(kσ + p )}
k=1
1 −Pr{x ≤n(kσ + p )} =1 −Pr{x ≤100(1(0.0100) + 0.01)} =1 −Pr{x ≤2}
2 ⎛100 ⎞
=1 − ∑ ⎜ ⎟(0.01) x (1 −0.01)100−x
x =0 ⎝ x ⎠
⎡⎛100 ⎞ ⎛100 ⎞ ⎛100 ⎞ ⎤

=1 −⎢⎜ ⎟(0.01)0 (0.99)100 + ⎜ ⎟(0.01)1 (0.99)99 + ⎜ ⎟(0.01) 2 (0.99)98 ⎥
⎣⎝ 0 ⎠ ⎝1 ⎠ ⎝2 ⎠ ⎦
=1 −[0.921] =0.079
k=2
1 −Pr{x ≤n(kσ + p )} =1 −Pr{x ≤100(2(0.0100) + 0.01)} =1 −Pr{x ≤3}
3 ⎛100 ⎞ ⎡ ⎛100 ⎞ ⎤
=1 − ∑ ⎜ ⎟(0.01) x (0.99)100−x =1 −⎢0.921 + ⎜ ⎟(0.01)3 (0.99)97 ⎥
x =0 ⎝ x ⎠ ⎝3 ⎠
⎣ ⎦
=1 −[0.982] =0.018
k=3
1 −Pr{x ≤n(kσ + p )} =1 −Pr{x ≤100(3(0.0100) + 0.01)} =1 −Pr{x ≤4}
4 ⎛100 ⎞ ⎡ ⎛100 ⎞ ⎤
=1 − ∑ ⎜ ⎟(0.01) x (0.99)100−x =1 −⎢0.982 + ⎜ ⎟(0.01) 4 (0.99)96 ⎥
x =0 ⎝ x ⎠ ⎝4 ⎠
⎣ ⎦
=1 −[0.992] =0.003
3-24
3.35.
This is a hypergeometric distribution with N = 25 and n = 5, without replacement.
(a)
Given D = 2 and x = 0:
⎛2 ⎞⎛25 −2 ⎞
⎜ ⎟⎜ ⎟
⎝0 ⎠⎝ 5 −0 ⎠ (1)(33, 649)
Pr{Acceptance} = p (0) = = =0.633
⎛25 ⎞ (53,130)
⎜ ⎟
⎝5 ⎠

(1) Excel Function HYPGEOMDIST(x, n, D, N)
(2) MTB > Calc > Probability Distributions > Hypergeometric

Hypergeometric with N = 25, M = 2, and n = 5
x P( X <= x )
0 0.633333
(b)
For the binomial approximation to the hypergeometric, p = D/N = 2/25 = 0.08 and n = 5.
⎛5 ⎞
Pr{acceptance} = p(0) = ⎜ ⎟(0.08)0 (1 −0.08)5 = 0.659
⎝0 ⎠
This approximation, though close to the exact solution for x = 0, violates the rule-of-
thumb that n/N = 5/25 = 0.20 be less than the suggested 0.1. The binomial approximation
is not satisfactory in this case.
(c)
For N = 150, n/N = 5/150 = 0.033  0.1, so the binomial approximation would be a
satisfactory approximation the hypergeometric in this case.
3-25
3.35 continued
(d)
Find n to satisfy Pr{x  1 | D  5}  0.95, or equivalently Pr{x = 0 | D = 5} < 0.05.
⎛5 ⎞⎛25 −5 ⎞ ⎛5 ⎞⎛20 ⎞
⎜ ⎟⎜ ⎟ ⎜ ⎟⎜ ⎟
⎝0 ⎠⎝ n −0 ⎠ ⎝0 ⎠⎝ n ⎠
p (0) = =
⎛25 ⎞ ⎛25 ⎞
⎜ ⎟ ⎜ ⎟
⎝n ⎠ ⎝n ⎠
try n =10
⎛5 ⎞⎛20 ⎞
⎜ ⎟⎜ ⎟
0 10 (1)(184, 756)
p (0) = ⎝ ⎠⎝ ⎠ = =0.057
⎛25 ⎞ (3, 268, 760)
⎜ ⎟
⎝10 ⎠
try n =11
⎛5 ⎞⎛20 ⎞
⎜ ⎟⎜ ⎟
0 11 (1)(167,960)
p (0) = ⎝ ⎠⎝ ⎠ = =0.038
⎛25 ⎞ (4, 457, 400)
⎜ ⎟
⎝11 ⎠
Let sample size n = 11.
3.36.
This is a hypergeometric distribution with N = 30, n = 5, and D = 3.
⎛3 ⎞⎛30 −3 ⎞
⎜ ⎟⎜ ⎟
⎝1 ⎠⎝ 5 −1 ⎠ (3)(17,550)
Pr{x =1} = p (1) = = =0.369
⎛30 ⎞ (142,506)
⎜ ⎟
⎝5 ⎠
⎛3 ⎞⎛27 ⎞
⎜ ⎟⎜ ⎟
0 5
Pr{x ≥1} =1 −Pr{x =0} =1 − p (0) =1 −⎝ ⎠⎝ ⎠ =1 −0.567 =0.433
⎛30 ⎞
⎜ ⎟
⎝5 ⎠
3-26
3.37.
This is a hypergeometric distribution with N = 500 pages, n = 50 pages, and D = 10
errors. Checking n/N = 50/500 = 0.1  0.1, the binomial distribution can be used to
approximate the hypergeometric, with p = D/N = 10/500 = 0.020.
⎛50 ⎞
Pr{x = 0} = p(0) = ⎜ ⎟(0.020)0 (1 −0.020)50−0 = (1)(1)(0.364) = 0.364
⎝0 ⎠
Pr{x ≥2} = 1 −Pr{x ≤1} = 1 −[Pr{x = 0} + Pr{x = 1}] = 1 − p (0) − p (1)
⎛50 ⎞
= 1 −0.364 −⎜ ⎟(0.020)1 (1 −0.020)50−1 = 1 −0.364 −0.372 = 0.264
⎝1 ⎠
3.38.
This is a Poisson distribution with  = 0.1 defects/unit.
e −0.1 (0.1)0
Pr{x ≥1} = 1 −Pr{x = 0} = 1 − p(0) = 1 − = 1 −0.905 = 0.095
0!

(1) Excel Function POISSON(, x, TRUE)
(2) MTB > Calc > Probability Distributions > Poisson

Poisson with mean = 0.1
x P( X <= x )
0 0.904837
3.39.
This is a Poisson distribution with  = 0.00001 stones/bottle.
e −0.00001 (0.00001)0
Pr{x ≥1} = 1 −Pr{x = 0} = 1 − = 1 −0.99999 = 0.00001
0!
3.40.
This is a Poisson distribution with  = 0.01 errors/bill.
e −0.01 (0.01)1
Pr{x = 1} = p(1) = = 0.0099
1
3-27
3.41.
Pr(t ) = p (1 − p )t −1 ; t = 1, 2,3,K
d ∞ 1
μ = ∑ t ⎡⎣ p (1 − p )t −1 ⎤⎦ = p ⎡∑ q t ⎤ =
∞
t =1 ⎢ ⎥
dq ⎣t =1 ⎦ p
3.42.
This is a Pascal distribution with Pr{defective weld} = p = 0.01, r = 3 welds, and x = 1 +
(5000/100) = 51.
⎛51 −1⎞
Pr{x = 51} = p (51) = ⎜ 3
⎟(0.01) (1 −0.01)
51−3
= (1225)(0.000001)(0.617290) = 0.0008
⎝ 3 −1 ⎠
Pr{x > 51} = Pr{r = 0} + Pr{r = 1} + Pr{r = 2}
⎛50 ⎞ ⎛50 ⎞ ⎛50 ⎞
= ⎜ ⎟0.010 0.9950 + ⎜ ⎟0.0110.9949 ⎜ ⎟0.012 0.9948 = 0.9862
⎝0 ⎠ ⎝1 ⎠ ⎝2 ⎠
3.43.
x ~ N (40, 52); n = 50,000
How many fail the minimum specification, LSL = 35 lb.?

⎧ 35 −40 ⎫
Pr{x ≤35} = Pr ⎨z ≤ ⎬= Pr{z ≤−1} = Φ (−1) = 0.159
⎩ 5 ⎭
So, the number that fail the minimum specification are (50,000)  (0.159) = 7950.

(1) Excel Function NORMDIST(X, , , TRUE)
(2) MTB > Calc > Probability Distributions > Normal

Normal with mean = 40 and standard deviation = 5
x P( X <= x )
35 0.158655
How many exceed 48 lb.?

⎧ 48 −40 ⎫
Pr{x > 48} = 1 −Pr{x ≤48} = 1 −Pr ⎨z ≤ ⎬= 1 −Pr{z ≤1.6}
⎩ 5 ⎭
= 1 −Φ (1.6) = 1 −0.945 = 0.055
So, the number that exceed 48 lb. is (50,000)  (0.055) = 2750.
3-28
3.44.
x ~ N(5, 0.022); LSL = 4.95 V; USL = 5.05 V
Pr{Conformance} = Pr{LSL ≤ x ≤USL} = Pr{x ≤USL} −Pr{x ≤LSL}

⎛ 5.05 −5 ⎞ ⎛ 4.95 −5 ⎞
=Φ⎜ ⎟ −Φ ⎜ ⎟ = Φ (2.5) −Φ(−2.5) = 0.99379 −0.00621 = 0.98758
⎝ 0.02 ⎠ ⎝ 0.02 ⎠
3.45.
The process, with mean 5 V, is currently centered between the specification limits
(target = 5 V). Shifting the process mean in either direction would increase the number
of nonconformities produced.
Desire Pr{Conformance} = 1 / 1000 = 0.001. Assume that the process remains centered
between the specification limits at 5 V. Need Pr{x  LSL} = 0.001 / 2 = 0.0005.
Φ ( z ) = 0.0005
z = Φ −1 (0.0005) = −3.29
LSL −μ LSL −μ 4.95 −5

z= , so σ = = = 0.015
σ z −3.29
Process variance must be reduced to 0.0152 to have at least 999 of 1000 conform to
specification.
3.46.
x ~ N ( μ , 42 ). Find μ such that Pr{x < 32} = 0.0228.
Φ −1 (0.0228) =−1.9991
32 −μ
=−1.9991
4
μ =−4(−1.9991) + 32 =40.0
3.47.
x ~ N(900, 352)
Pr{x > 1000} =1 −Pr{x ≤1000}
⎧ 1000 −900 ⎫
=1 −Pr ⎨x ≤ ⎬
⎩ 35 ⎭
=1 −Φ(2.8571)
=1 −0.9979
=0.0021
3-29
3.48.
x ~ N(5000, 502). Find LSL such that Pr{x < LSL} = 0.005
Φ −1 (0.005) = −2.5758
LSL −5000
= −2.5758
50
LSL = 50(−2.5758) + 5000 = 4871
3.49.
x1 ~ N(7500, 12 = 10002); x2 ~ N(7500, 22 = 5002); LSL = 5,000 h; USL = 10,000 h
sales = $10/unit, defect = $5/unit, profit = $10  Pr{good} + $5  Pr{bad} – c
For Process 1
proportion defective = p1 =1 −Pr{LSL ≤ x1 ≤USL} =1 −Pr{x1 ≤USL} + Pr{x1 ≤LSL}
⎧ 10, 000 −7,500 ⎫ ⎧ 5, 000 −7,500 ⎫
=1 −Pr ⎨z1 ≤ ⎬ + Pr ⎨z1 ≤ ⎬
⎩ 1, 000 ⎭ ⎩ 1, 000 ⎭
=1 −Φ(2.5) + Φ(−2.5) =1 −0.9938 + 0.0062 =0.0124
profit for process 1 = 10 (1 – 0.0124) + 5 (0.0124) – c1 = 9.9380 – c1
For Process 2
proportion defective = p2 =1 −Pr{LSL ≤ x2 ≤USL} =1 −Pr{x2 ≤USL} + Pr{x2 ≤LSL}
⎧ 10, 000 −7,500 ⎫ ⎧ 5, 000 −7,500 ⎫
=1 −Pr ⎨z2 ≤ ⎬ + Pr ⎨z2 ≤ ⎬
⎩ 500 ⎭ ⎩ 500 ⎭
=1 −Φ(5) + Φ (−5) =1 −1.0000 + 0.0000 =0.0000
profit for process 2 = 10 (1 – 0.0000) + 5 (0.0000) – c2 = 10 – c2
If c2 > c1 + 0.0620, then choose process 1
3-30
3.50.
Proportion less than lower specification:
⎧ 6 −μ ⎫
pl = Pr{x < 6} = Pr ⎨z ≤ ⎬= Φ (6 −μ )
⎩ 1 ⎭
Proportion greater than upper specification:
⎧ 8 −μ ⎫
pu = Pr{x > 8} = 1 −Pr{x ≤8} = 1 −Pr ⎨z ≤ ⎬= 1 −Φ(8 −μ )
⎩ 1 ⎭
Profit = +C0 pwithin −C1 pl −C2 pu

= C0 [Φ (8 −μ ) −Φ (6 −μ )] −C1[Φ (6 −μ )] −C2 [1 −Φ (8 −μ )]
= (C0 + C2 )[Φ(8 −μ )] −(C0 + C1 )[Φ (6 −μ )] −C2
d d ⎡8−μ 1 ⎤
[Φ (8 −μ )] = ⎢ ∫ exp(−t 2 / 2)dt ⎥
dμ d μ ⎣ −∞ 2π ⎦
Set s = 8 –  and use chain rule
d d ⎡s 1 ⎤ ds 1
dμ
[Φ (8 − μ )] = ⎢ ∫
ds ⎣−∞ 2π
exp(−t 2 / 2)dt ⎥ =− (
exp −1/ 2 × (8 − μ ) 2 )
⎦dμ 2π
d (Profit) ⎡ 1 ⎤ ⎡ 1 ⎤
dμ
= −(C0 + C2 ) ⎢ ( )
exp −1/ 2 × (8 − μ ) 2 ⎥ + (C0 + C1 ) ⎢ ( )
exp −1/ 2 × (6 − μ ) 2 ⎥
⎣ 2π ⎦ ⎣ 2π ⎦
Setting equal to zero
(
C0 + C1 exp −1/ 2 × (8 − μ )
=
2
)
= exp(2 μ − 14)
(
C0 + C2 exp −1/ 2 × (8 − μ ) 2 )
1 ⎡ ⎛ C + C1 ⎞ ⎤
So μ = ⎢ln ⎜ 0 ⎟ +14 ⎥ maximizes the expected profit.
2 ⎣ ⎝ C0 + C2 ⎠ ⎦
3-31
3.51.
⎛n ⎞ x
For the binomial distribution, p ( x) = ⎜ ⎟ p (1 − p) ; x = 0,1,..., n
n −x
⎝x ⎠
∞ n ⎡⎛n ⎞ ⎤
μ = E ( x) = ∑ xi p ( xi ) = ∑ x ⎢⎜ ⎟ p x (1 − p ) n − x ⎥ = n ⎡⎣ p + (1 − p )⎤⎦ p = np
n −1
i =1 x =0
⎣⎝ x ⎠ ⎦
σ 2 = E[( x − μ ) 2 ] = E ( x 2 ) − [ E ( x)]2
∞ n ⎡⎛n ⎞ n− x ⎤
E ( x 2 ) = ∑ xi2 p( xi ) = ∑ x 2 ⎢⎜ ⎟ p x (1 − p ) ⎥ =np + (np) 2 − np 2
i =1 x =0
⎣⎝ x ⎠ ⎦
σ 2 = ⎡⎣np + (np) 2 − np 2 ⎤⎦ − [np ] = np (1 − p)
2
3.52.
e −λ λ x
For the Poisson distribution, p ( x) = ; x = 0,1,K
x!
⎛ e −λ λ x ⎞ −λ ∞ λ ( x −1)
()
∞ ∞
μ = E[ x ] = ∑ xi p ( xi ) = ∑ x ⎜ ⎟= e λ ∑ =e −λ λ eλ = λ
i =1 x =0 ⎝ x! ⎠ x =0 ( x − 1)!
σ 2 = E[( x − μ ) 2 ] = E ( x 2 ) − [ E ( x)]2
2
∞
2 ⎛ e −λ λ x ⎞
∞
2 2
E ( x ) = ∑ x p( xi ) = ∑ x ⎜
i ⎟= λ + λ
i =1 x =0 ⎝ x! ⎠
σ 2 = (λ 2 + λ ) − [λ ] = λ
2
3-32
3.53.
For the exponential distribution, f ( x) = λ e −λ x ; x ≥0
For the mean:

( )
+∞ +∞
μ = ∫ xf ( x)dx = ∫ x λ e − λ x dx
0 0
Integrate by parts, setting u = x and dv = λ exp(−λ x)

+∞ 1 1
uv − ∫ vdu = ⎡⎣− x exp (−λ x )⎤⎦0 + ∫ exp (−λ x )dx = 0 + =
+∞
0 λ λ
For the variance:

2
2 2 2 2 ⎛1 ⎞ 2
σ =E[( x −μ ) ] =E ( x ) −[ E ( x) ] =E ( x ) −⎜ ⎟
⎝λ ⎠
+∞ +∞
E ( x 2 ) = ∫ x 2 f ( x )dx = ∫ x 2 λ exp(−λ x)dx
−∞ 0
Integrate by parts, setting u = x 2 and dv = λ exp(−λ x)

+∞
+∞ 2
uv −∫vdu = ⎡⎣x 2 exp(−λ x) ⎤⎦ + 2 ∫x exp(−λ x)dx = (0 −0) +
0
0
λ2
2 1 1
σ2 = 2
− 2 = 2
λ λ λ
3-33

CH 03

Uploaded by

Copyright:

Available Formats

CH 03

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CH 03

Uploaded by

Copyright:

Available Formats

Chapter 3 Exercise Solutions

MTB > Graph > Histogram > Simple

MTB > Graph > Histogram > Simple

MTB > %hbins 12.5 17 .5 c7

median observation rank is (0.5)(80) + 0.5 = 40.5

Q1 observation rank is (0.25)(80) + 0.5 = 20.5

Q3 observation rank is (0.75)(80) + 0.5 = 60.5

90th percentile observation rank is (0.90)(80) + 0.5 = 72.5

Time may be an important source of variability, as evidenced by potentially cyclic

⎧1/ 36; x = 2 2 / 36; x = 3 3 / 36; x = 4 4 / 36; x = 5 5 / 36; x = 6 6 / 36; x = 7

This is an exponential distribution with parameter =1.

p( x) = kr x ; 0 < r < 1; x = 0,1, 2,K

This exercise may also be solved using Excel or MINITAB:

⎛50 ⎞ ⎛50 ⎞ ⎛50 ⎞

Pr{ pˆ > kσ + p} = 1 −Pr{ pˆ ≤kσ + p} = 1 −Pr{x ≤n(kσ + p )}

⎡⎛100 ⎞ ⎛100 ⎞ ⎛100 ⎞ ⎤

This exercise may also be solved using Excel or MINITAB:

Cumulative Distribution Function

This exercise may also be solved using Excel or MINITAB:

Cumulative Distribution Function

How many fail the minimum specification, LSL = 35 lb.?

This exercise may also be solved using Excel or MINITAB:

Cumulative Distribution Function

How many exceed 48 lb.?

Pr{Conformance} = Pr{LSL ≤ x ≤USL} = Pr{x ≤USL} −Pr{x ≤LSL}

LSL −μ LSL −μ 4.95 −5

If c2 > c1 + 0.0620, then choose process 1

Profit = +C0 pwithin −C1 pl −C2 pu

For the mean:

Integrate by parts, setting u = x and dv = λ exp(−λ x)

For the variance:

Integrate by parts, setting u = x 2 and dv = λ exp(−λ x)

You might also like