CHAPTER<!

4·>. a) P(l <X)= Je- xdx = (- e- x)I"' = e-

00
1
1= 0.3679
I
2.
b) P(l < X < 2.5) = Je- xdx = (-e-x)~ -> =
15

I I
e- 1- e- 2-5 = 0.2858

c) P(X = 3) = Je- xdx = O

J

'J

0 P(x < X) = J,- xdx = (- e- x) x

00 11>0
= , - x = 0.1 0
X
T~.en.x =- ln(0 .1 0 ) = ~,3.

&l P(Xsx) = JX e- xdx = (- e- x) IX=l- e- x = O.lO

0 0
T~.en.x = -ln(0.9) = 0 .1054

4 ·:). a) P(X < 0) = J 0.5cosxdx = (0.5sinx)l

0 0
- -:r/ 2
= 0 - (- 0.5) = 0.5
- o/2

bl P(X < - -rrl 4) = J 0.5 cosxclx = (0.5sinx)l-"

- -:r/ 4

- ':r/2
/4
=- 0.3536 - (- 0.5) = 0. 1464
- -:r/ 2
<:r/4

c) P(- -rr I 4 < X < -rr 14) =

J
- -:r/4
0.5 cosxdx = (0.5 sin x) [. /4
<:r/ 4
= 0.3536 - (- 0.3536) = 0.7072

dl P(X > - -rr I 4) = J 0.5 cosxdx = (0.5sinx >I"

<:r/2 12

- -:r/ 4
= 0.5 - (- 0.3536) = 0.8536
- -:r/4

J 0. 5cosxdx = (0.5 sinx)lx

X

•l P(X < x) = = (0.5sinx) - (- 0.5) = 0.95

- ':r/2
- -:r/2
T~.en. sinx = O.<).and x = l .n (}.l) radians.
 4 4
x x2 42 - "2
J
4·5- 8) P(X < 4) =
J A

'
- dx = - =
8 16
3
16
= 0.4375.~>=,..fx(xl=Oforxq

4 4
x x2 42 - 32
b) P(X< 4)=
J - dx = - =
' 8
'
16
3
16
= 0.437) bilca,..fx(xl=Oforx >;

5 x x2 [ 52 - 42
c) P(4<X<5) = J - dx = - = = 0.562 5
4 8 16 16
4.5 2 .5 2 2
4.5 - J-. -- 0.-IO'J 1
dl P(X< 4.5) = - dx = - =
38 163 J--
16
X X

sx J3.S,.- dx = x2[ + -x2 ;.> = 52 - 4.52 + '52

J.
- ,2
J = 0.5
•l P(X> 4.5)+P(X<3.5) =
J - d,- +
4.5 8 3 8 16 .5 16 J 16 16
4·7. a) l{o <X)=O,s.bys)mmetry.
I I
2 3
b) P(0.5<X) = J 1.5x dx = 0.5x 1 = 0.5 - 0.0625= 0.4375
0.5
0.5

cl P(- 0.5sXs0.5) = J 1.5x dx = 0. 5x

0.5

- 0.5
2 3
0.5
1
- 0.5
= 0.125

d) P(X < -:l)=O

e) P(X < o or X>- o,s) = 1

0 P(x <X) = JX
1.5x2 dx = 0.5x31
: = 0.5 - 0.5x 3 = 0.05
Theo.x = O:~.;s

4-9. 8) P(X >50) = J 1.0dx = b t

50.25 50.25
= 0.5
50
50.25 Sil.25
b) P(X>x) = 0.90 = J 2.0dx = 2xlx =1 00.5- 2x
X
Then,~= <)9.6andx = 49.8

4-11. a) P{X < 2.2,5 or X> 2.7.;) = P(X < ~.:!.5)- P{X > 2.7.;) boollnse the two t'\'ttll$ate mutuaJiyexclusiw:. n.en.
2.8
P(X < :l.2..j) = 0 and P(X > :L75) = J 2dx = 2{0 .05) = 0 .10
2.1 5
b) If the probabilityd-ensity function isoeotcri!dst :l,s.; mcters, thenfx(x) = :l for :l.3 < x < :l.Sandall rods "'ill meet specificatioll$.
 4·l j. a) P(X < 2.8) = P{X s -2.8) bee!! use X iss cnntin.-ollS random variable.
Tr.en. P(X < ~.8) = A,i.S) = <U{~.S) = o..;6.
b) RX> 1-5) = 1-RX ~ 1-5) = l-O.i ( lS) = 0 .7
c) RX < -~) = Fx{-i) = o
d) IV<>6)=l-FX(6)=0

4·17. NowJ{x) = o.:; 006Xfot- rt/2 < x < st/~and

J 0. 5cos udu = (0.5sinx)lx

X

Fx (x) = = 0.5sinx + 0.5

- .;rf2
- .;rf2,

O,x 5 - 1T 12
Fx(x) = 0.5sin x + 0.5, - -rr / 2 5 x < -rr / 2 .
Tlten.
I , x ?.T. / 1

.,
0,x< J
, .2 - 9
' 3< x <5 .
foro< x.Th.en. 16 ' -
l,x > 5

JUly=2x -4.6
X

4·~l. Now.ftx)=2fori<.J<X < 2.8and F (x) =

2.3
for i,l < x < 2.8. TM:n.

0, ~· <~ 2.3

F (x ) = 2x -4.6, 2.3 s x <2.8.

1, 2.Ss x

RX > ~.7) = 1-FV<:;. i .7) = 1- R:2.7) = 1-0.8 = O.i becatse X is a continuous random \"ariable.
 4·'3· F(>')- J
X

0
0.5xdx = 0.5x
2
2
[ = 0.25x 2 foro <x < , ,Thtn.

0. x<O

O<x<2.

I.

/(x)- 0.2. 0< .r< 4

4·:!;.
0.04. 4 < x< 9

H7. £(X)=
.J 0.25xdx = 0.25:
, .-2
0 - 0

I 4 I

4·29. £(X) = J1.5x dx 3

= 1.5 ·: -0
- 1 -1
I I
I"(X ) = JL5x (x - 0) dr =J.5J x 4dx
3 2

- 1 -1

= X;
1.5-
5
L I
= 0.6
 8
3(8x - x2 ) x '- Jx ' ]
4-3 1. E (X) = 8 x
J0 dx = [- -- = (16 -1 2) - 0 = 4

l
256 32 1024 0

V(X) = J8 <x -4/>'(8 x- x2) dx = J8 - 3 x• +_:_

0 256
3 , I_ 2 _
- ~+ >X
0 2 56 16 16 2
rx

8
V(X)=[- Jx5 +Jx' _ 5x3 +3x2 ] = [ - 384+ 192 -1 60+ 48]= 3.2
. 1280 64 16 4 5
0

4-35. a) E(X) = !120 600 = 600 1n x 1120 =1 09.39

x-'-'-'-dx
x 2- 100
100

V(X) = J
100
(x -I 09.39)2 600 dx = 600J 1- 2(109.39) +(I 09.39)2 dx
x2 JOO x x2
120
= 600(x - 2 18.78 1n x -1 09.392x - 1) = 33 . 19
1100

00

• ·J7. •> E(X )= J x i Oe-iO(x- S)dx.

£(X) = - xe-IO(x- 5)
l
~
Joo
5
s
Using integNtion bypsrts "'ith tt = x aodd11 = 10e

+
5
-to(r-sl

, -IO(x- 5)dx = 5- e
I0
dx, we obtain
-IO{x- 5) r
5
= 5. 1.

Now, Jl (X) = J
«>
(x - 5. J)2 JOe-IO(x-
2
5) d\· , Using th.e integtationbyparts,-.itb 11 = (x-.;.1) and:dv = lOt-lO{X-s). \l.'tobtaio

V (X) = - (x -5 5. 1)2 e-lO(x - S) ·I"' + 2J

"" (x - 5. 1)e-IO(x- 5) dx. From tf!.cdefinitionof~X)theintegral abo\'t' istt."OOgni7.«i toequal o.
' 5 5
Therefore. V{X) = {5-.;.1) = 0 .01.

b) P(X > 5. 1) = J
06
I Oe-iO(x- 5)dx = - e -IO{x- 5)1
""

~I
= e -10{5.1-5) = 0.3679
5.I
 4-39· a) E.OO = {- 1• l)/ 2 = o.
2
V(X) = (l - (-l)) 1/J,andox=O.;n
12
X I X
b) P(- x < X < x) = J - dt = 0.511 = 0.5(2x) = x
2 -x
-x
Therefo re. x slt.onld eqooJ o .90.

0, x < -1
F(x) = 0. 5x +0.5, -l ::; x< l
c)
I' I ~ x

4-41. a) TltedistributionofXisj(x) = u) for i'L9.S < x < 1.0.5. Noh·,

0, x <0.95

Fx(x) = I Ox - 9.5, 0.95~ x< 1.05

I' 1.05 ~ X

b) JV<>l.02) = 1- JV( Sl.02) = l- Fx(l.02) = 0~

<:) lt P(X > >:) = 0.91), th.eo 1- HX) = 0 .90 and F{X) = 0 .10. Th.erefo te,lOX- 9..; = 0 .10 and>: = 0.¢ .

(1.05- 0.95)2
d) E.{X) = (1.0.5 • 0.9.:;)/ 2 = l .OO and V(X) = = 0.00083
12
4-43. a) ThedistribntionofXisj(x) = 100 for o .~o.so < x < o.:Hso.Therefo re.

0, x <0.2050

F(x) = IOOx - 20.50, 0.2050~ x< 0.2 1 50.

I, 0.2 1 50 ~ x

b) RX > 0 .212.5) = l- 1\0.212.5) = l-l t00(0.2li.S)-20..;o J= 0 .2.5

<:) lfP(X > x) = 0 .10, then 1- ftX) = 0 .10 and F{X) = 0 .91). Therefore,lOOX - 20..;0 = 0.90 and>:= 0 .2140.
?
(0.2150- 0.2050t -6 •
d) E.{X)= (O.iO.SO -0.21.50)/ 2 =0.2.100¥tnandV( X)= ? =8j$Xl0 Jlffi
I_
4--45. (a) l.ct X be t~.etime (in minutes) bef\,·~narri\'<11 and 8:;}0 am.
I
j(x) = - . f or 0 s x!: 91).
90 X
SotlteCOFis}{x) = - .joJ'O ::x s 9Q.
90 •
(b) f;(X)=4.S.Var(X)=90 / 12- =67.5
(c) Thet'\l:nt isananh'al in f.t!.i! intervaJs 8:.:;0 -9:00am or <)::.oo -9:30am or 9:.50 - 10:00 sm so t~.at IJ!.e probability= j0/ 90 = 1/ :.}.
(d) Similarly, flt.e e\'ent is anarri\'<IJ in tl'.e iotervsls8:30 -8:40am or 9:00 - 9:10 sm or 9:30 -9:40am so that t~.o: probabili ty= :J0/ 90 = t/:.J.
 4-47. {a) tet X be th.earrivaJ time(io mim:.tes)after 9:00am.

l'{X) =
(120 - ol =1200andax=.')4JJ4.
12
b) Wewomt to determine the probability the mess.sgeatri\'es inanyofth.c follo\.>o;ng inteNa!s:
9:05- 9:1.; amor 9:35- 9:45am o r 10:05- 10:1samor 10:35 -10:45 am. n-£prob3bilityofthise>.l:nt is40/l~O = t/ j..
c) We want todd ennine tfo.e probabilityt~.e mess.ageatri\'CS inanyoftf!.£ follo\.>oiQg. inter\'als:
9:15-9:30 amor 9:45- 10:00 a m or 10:15- tO:jO sm o r 10:4.;- u :oo a m. Tlt.e probability oftbis ~tisGoft'J.O = l/ 2

4-49. a) P('l < 1;.32) = 0 .91)6.;8

b) P{l < j .O) = 0 .9()86.;
<:) P{l > 145) = 1-0.92647 = O.Oi.J.5j.
d) P(Z >- 2.1.;) = p(Z < ~Ll.;) = 0 .9&$1!!
c) F(- :!,34 < z < 1.76) = P{l < 1.76)- P(Z> 1,34) = 0 .9.;116
4 -.;1. a ) P(Z< 1.28) = 0.90
b) P(Z < O) =O.S
c) (f P(Z > z) = 0 .1. then P(Z < z) = 0 :!)1) and z = 1.18

d) lfP(Z > 1.) = 0 .9. then P(Z < 1.) = 0 .10 andz = -1.28
d F(- 1.::!4 < Z < z) = P('L < z)- P('L < -1.::!4)
= P{Z < 7.) - 0.10749.
Th.erefore. P{Z < l) = o.B ... 0 .10749 = 0 .9Q749andt. = 1,33

4·.53· a ) PCX< l.))= P(Z < (lJ-10)/~)

= P(Z< 1.))
=0.9.)319
b) P(X>9)= >- P(X< 9)
= 1- P{l.-< (9-10)/1)
= 1- FfL< -o..;)
=0.69146.

cl P(6 <X<>4l = P
6-10
l <2< 14-10]
[ 2
= F(- 2<Z< 2)
= P('L< 2)- P(Z <- 2)1
= 0.9.;45

2-10 4-10]
dl P(' <X«l = P
[ 2 <2< 2
= P(-4 <Z< -J)
= 1'('/. < - j ) - I'V- < - 4)
= O.OOlj.!!
e) P(- 2<X<8) =P(X<8) -P(X < -2)

p[ 2 < 8 - 10]- P[ 2 < -2~ 10]

=

=P<Z<-l) -P(Z < -6)

2
= 0 .1.;866
 4·55· a) I'(X< u) • P[z< I I~ 5 ]
• P(7. < J.,S)
•0.93319

b) I'()(>O)•P Z> -0- -5)

[ 4
• P(1. > .. u.s)
• l - P(7. <.. 1.2,$)
• •.89435
3-5 7- 5]
<) I'U<X<7l•
[ 4- <Z < -4-
P-
• P(-O.S < Z< O.S)
• P(1. < 0._11) .. fl(Z<- O,S)
• 0 ,18:192.

d) PH < X<9l • P
- 2- 5<Z<-
9--5]
[ 4 4
• N.- J.7.S <z< J)
• P("l. < 11 ... P(Z <- ,.,su
• o.Bcn:tB

'-5 8- 5)
t) P(><X<SI • P
[=-;--<Z< - 4-
• F(·0.15<Z<o.;s)
• m < o.:s)- P(Z < - o.;s)
• 0.$4674

6250100
- 6000]
4•57· •I P(X<6250)= P
[ Z<
• P(7. <1.S)
"" 0.993?9

b) P<.58oo <X (5900) = P

5800- 6000 < Z < .:.c:...:..:,-:7c:..:.~
5900- 6000]
[ I 00 100
• P(· 2<Z<-J)
•l'tZ<->)- PCl.<-2)
'"0.J3$Cn

<l P(X > X) • P Z> ·

[ ·-6000]
100
=0.95_,.,..,.,.... -··-6000
-:-::::-- • -1.65 andx=;S:ls
100
4'59- (a)14(2)•0.0218
(b) Lt1Xdmcy<U.6PH.
X- ~(129,14 )

RX <ton) • <.() 100-129 ] = 4><-1.07141 = o.ott;t6

[ 14
_,
{<:) <D (0.9,5)Jit14 •1:t9= 1,51.02:80
9.;9fiof 1~Al$UI"&trle& will be fini&I>.OO. with.io 152.02:8 mim:.tes.
(d) 1C)Q>>1!1:l.O:.t8ao Uw: w lumcot s~hs1!.rgcrics is \oerysmall (leu ih.nn,s9{.),
 4~>1 . a) P(X > of>:l_) = P[z>-0.62-0.05--0.5]
-
=PfL > :.!4)
=l - ffL<24)
= 0 .0082

b) P(04 7 <X< 0 .6.)) = . P 0.4 7 - 0.5 < z < ..:..:

0..::63'-:---:-0..:..:
.5 ]
[ 0.05 0.05
= P(- 0 .6 < Z< 2.6)
= P(Z < 2.6) - P(Z < - 0 .6)
= 0 .99.;j4- 0 .21425

c) ~ «l = P(X < x) = P[z< x0.05

- 0.5 ] = 0.90.

Therefore. x - O.S = 1.28andx = o ..;64.

0.05

4-63. a ) If ~ > >') =0.99\).then P Z > 12 - '' ] = 0.999

[ 0. I
12 - JL
Tltcrefore. = - j .09 aod11 = l :l$09
0. I

b) lfP(X> » ) =0.99\).thco P Z > 12 - .u·] = 0.999

[ 0.05
Therefore.
12 - JL =- ;3.09aod;~ = 12.1545
0.05

4-65. a ) ~ > 70l = P l > 70 - 60]

[ 4
=l-W.< ::!..;)
= 1-0.99379 = O.OOM.l

b) ~qs)= P[z< 58 ~ 60]

= RZ<-O,s)
= 0.:)08538
c) 1.ooo.ooo h)1es·s bits/b)1e = s.ooo.ooo hits

8,000,000 bits
I33.33 secoods
60,000 bits/sec
4-67 l.etXdenote theheigJtt.
2
X - N(l4 1. 0 .01 )

<al P(X > 1.42) =I- P(X < 1.42) = 1- q,[ l .42 - 1.4 1]=I- q,(l) = 0. 1587
0.0 I
-I
{b) <I> ( 0 .0S) KO.Ol- 14l=l ,.l9$6

!cl
0.01 0.01
l
P(l .39 < X < I.43) = of>[ 1.43 - 1.4 I]- of>[ 1.39 - I.4 l = .P(2) - .P(- 2) = 0.9545
 4.£>!). a) P!XqOOO) = p 5000 - 7000 ]
l < ==-,-=:.
[ 600
= P(Z < - .3..'.13) = 0 .0004,3

bl P!X>xl=0.9s.T~.cr.rou. P[z> x~~OOO] = 0 .95 and X 7000 =_ (.64

600
Cons.eqnently.x = 6016.

cl P(X > 7000)=

l
P [ Z > 7000 - 7000 = P(Z > 0) = 0.5
600
P(t.J!.r« laserso)X!toltingafter 7000 hours) = {l/'J } = 1j8

4-71. al P(X > 13) = P [Z > 13 -1 2] = P(Z > .2) = 0.0 22 75

0.5

b) lfP!Xo3)=o.m .w.eo P Z < 13-1 2] = 0.999

[ 0
Therefore.!/ a= .J.i>9aod =a 1/ .).09 = 0,3:24

c) II P!Xo3) =o.m .w.eo P

[Z < 13-p
, ]
0.)
= 0.999

nnefote,
13- .u =,3.09Sod,!l=ll455
0.5
4·7,3. From tho:sltapeoftft.e normal cut\'C the probability is maxim ius (or an intet\'al S)'lllmetricaixmt the mean.
Tttercl'orea = 2.1-5 witll probability= 0 .19']4. The standard a'e\iationdoes notaffect tt.ec~.oioe:of intm'l'l l.

4 ·15· a) P(X >lOO) = P Z> 100 - 50.9] = P(Z >l.9()4)=0.0::!48

[ 25

b) P(X < 2,5) = p Z < 25- 50.9] = P{"/. < - 1:0.}6) = 0 .1501
[ 25
-1
c) P(X > :.:) = o.o.;. tlten<l> {0:9,s)x~·.;0 .9 = 1.f*l9x2.5-50 .9 = 92.M1.)

4 ·77. a ) F..(X) = 200(04) = 80. V{X) = 200(04X0.6) = 48and0'X = .J48

Thco, P(X 570) ~ P[z570~80 ]= P(Z 5- 1.37) = 0.08 53

PrO < X<90) ~P [ f4iso <25 89.5-

70.5-
f4iso]= P(-I.J7<251.37)
,
b)

= 0.91466-0.08534= 0.8293

c)
Pr9.S < X 5 80.5)~ P[ 79~SO < Z < 80~80 ]= P(- 0.072 17 <2 5 0.072 17)
= 0.0575
 4·79 z = X0)6;
- 64 X - 64 isapproxim.stelyN(O,l)
8

<•l P(X > 72) = 1- P(X ~ 72) = 1- P Z ~[ 72-64]

8
= 1-IV-~1) = 1-o.&u,l = o.1,s87
lfa oontinl!.ityoorrection '"ert:nsed tlt.t: fol!o,,;ng result is obtained.

P(X > 72) = P(X > 73) ~ P[z 2 73 - 0~5 - 64]

'"P(Z > 1.06) = 1- 0.855428 = 0. 1446

{b) o ,s
lfa oontinl!.ityoorrection '"ert:tl.SOO tlt.t: follo"'ing res-ult is obtained.

P(X < 64) = P(X < 63) ~ P[z ~ 63+ 0~ 5 - 64]= P(Z ~ - 0.06) = 0.4761

(c) K60 <X<68) =~<6S)-~s 60) = of>

[
68-S 64] -of> [60-64]
S
= ¢(O,s)-<li(-O,s) = O.j.8::!9
Ifa oontinliityoorro::tionwere us.ed the following re.sult is obtained.

P(60 < X< 68) = P(61~ X ~ 68)'" p[61- 0~5 - 64 < z < 68+ 0~5- 64]
~ P(- 0.44 < Z <0.56) = 0.3823

4-Bl. tct Xd~to: tt.e nu.mb.."t of poopl e ,,;t~.a disability in tlt.O!samp!e.

X - 81N(lOOO,O.l})3)
Z = X -1 000x0.193 X -1 93
J 193(1-0. 193) 12.4800
is approximately t\(0.1)

!al P(X > 200) = 1- P(X ~ 200) = 1- P(X ~ 200 + 0.5) = 1- .P[ 2005 -
193
]= 1- <!>(0.6) = 0.2743
12.48

!bl P(180< X < 300) = P(181<X ~ 299) = q,[ 299.5-1 93]- <I>[ 180.5 -1 93 ]
12.48 12.48

4-83. td X denote the number of original component$ that fail during tlt.e-..sefullifeof the prodnct. Then, X is a binomial random \"ariablewith p = 0 .001 and n = .:;ooo.

P(X > 10)'" P[z ?:: r-

Also. E.{X) = 5 MO {0.001) = 5 aod V( X) = 5000(0.001X0.999) = 4.99.;.

4.995
5
] = P(Z ?:: 2.01) = 1- P(Z < 2.01) = 1- 0.978 = 0.022
 2 4 4
4-85. l.et Xd:eoote the: number of p.'lrticles in JO <'Jn ofdust. n.en. Xi.sa Poisson random variab!e,.,;tn A = tO{looo)-= to.ooo.Aiso, E.(X) =A= 10 and V(X) = i. = 10

P(X > 10000) = 1- P(X < 10000) ~ I- P[z ~ I OO~O- IOOOO]~ I- P(Z < 0)~ 0.5
I0000
If a oontinu.ityoorrection \,·en USi'd: tl:e follo,..-ing tf$u.J t isobtaiood.

P(X > 10000) = P(X ?:: I0001) ~ P [z > LOOOI~ O.S - 1OOOO]~ P(Z > 0) ~ 0.5
10000
4-87. l.d Xdeootet~.e rmmbcrofhits to a website. Tben.Xisa Poisson random \'ariablewitha mesnof ,\ = 10.000 hits perday.Aiso. E(X) = ..\ = 10.000 = V{X).

a)
P(X> 20000) = I- P(X ~ 20000)= I- P[ z ~ 20000 - IOOOO ]
0J10000
= I- P(Z ~ I00)"" I- I = 0
lf a oontinuityoorr-ection ,,·ere toed lite follo,-ring result is obtained.
. -
P(X> 20000) = P(X ?:: 2000 1)~ P[ Z ?:: 20000- 0.5 - IOOOO ]
.JI0000
= P(Z ?:: 99.995)"' I- I= 0

bl P(X <9900) = P(X ~ 9899) = P[z ~ 98 j- 1

OOOO = P(Z
10000
l ~ - 1.0 I) = 0. I 562
lfa oontin"ityoon-ectionwereoed the following result is obtained.

P(X < 9900) = P(X ~ 9899) ~ P[z < 9899 + O.S- 1O, OOO] "' P(Z?:: - 1.0 I) = 0. I 562
J10ooo
x - 10000 ] x - 10000
c) lf'P(X>x) =O.Ol.f.l!.enP
[Z > .J = O.OI.n.erdore. = 2.33aodx = lj.jOO.
10000 10000
d) let Xdeootethenu.mbetofh.its to a website. Tlten.Xisa Poisson r.aodom \'ariable,ritha of mean 10.000 per day. F..(X) =A= 10.000 aod V{X) = 10.000.

P(X > 10200) - P[z?:: 10200 - 1OOOO ]= P(Z ?:: 2) = I- P(Z < 2)
.J10ooo
= I- 0.9772 5 = 0.022 75
If a oontim<.ityoorrflction is USi'd we obtain tlt.e follo,'ling result

P(X > I0, 200) ~ P[z?:: 10•2j.5-1O, OOO] = P(Z ?:: 2.005) = I- P(Z < 2.005)
I0,000
that approximatelyeq-u.aJs the NS-dt '"if.l!.out the oontin~<.ityoorrtction.

n.e expected number of<f.ttys v.ith more tft..an u),200 hits is{O .O~J.;)•j6.; = 8JO dsys per ~~r
e) tct Y dmoto: tf!.e nu.mb.."t of days per )'e.'lr ,.,.;t~over lO,:iOO f!.its to a ,,·ebsite.
TJ!..en. Y is a binomial 101ndom \'ariablewith n = j6.;aod p = 0 .0~27.; .
E(\') = 8..}0 and V(Y) = j6.;{0 .01~7.;XO:l>77i.5 ) = 8.18

P(Y > I 5) ~ P[z > 15j-8·30 ]= P(Z ?:: 2.56) =I- P(Z < 2.56)
8.28
=I- 0.9948 = 0.0052
 4-89. Witlt l O .,S~) O astJ!.ma incidents in children ina ::n-month period. th-en mean nu.mb.._r of incidents per month is t o.;o oj~l = .;oo. l.et Xdenotes Poisson modom\"ariablev.itha mean of .;~) 0
per month. Also. E(X) =A= .;oo = V(X).
a) Using a oontinu.ityoorrection. th.i!: follo,,ing ti$-dt is obtained.

P(X > 550) ~ P[ Z 2 550 +~ 500 l = P(Z > 2.2584) = 1- 0.9880 = 0.012

55
P(X > 550) = P[z 2 ~00 ]= P(Z 2 2.2361) = 1- P(Z <2.2361) = 1- 0.9873 = 0.0127
b) Using a a mtincityoorrcction, tbe follo,\ing resclt is obtained.

P(450< X < 550) = P(451<X< 549) = p[450.5- 500 < < 549.5- 500] z
- ' - - J 5oo - - J5oo
= P(Z s 2.2137)- P(Z s - 2.2137) = 0.9866 - 0.0134 = 0.9732

P(450< X <550) = P(X < 550) - P(X < 450) = P [z <

500
ss;- 500
500
]- P [z st 45 500
]

= P(Z s 2.236 1) - P(Z s - 2.2361) = 0.98 73 - 0.0127 = 0.9746

c) Jt\' s x) = 0.9.;
x = .p- 1(0.95)x v'5oo + 500 = 536.78
d) The Poissondistributionwould not be appropriate bcc.sl!SO: the rate of e>.'tntsshou.ld beoonsttlnt for a Poissondistribution.

Secoon+S

4-91. lfF..(:X)=lO,tl'.en..\ ::0.1

00 00

al P(X> 10) = J o. le- 0·" dx =-e-O.tx l = , -I = 0.3679

10
10
00

b) P(X>20) =-e- O. tx l = e- 2 = 0.1353

20
JO
c) P(X < 30) =-e- O.Ixlo = 1- e- 3 = 0.9502
X X
J o. ~«-0· 1 'dt =-e-0·"1
d) P(X < x) =
0
0 = 1- e-O.tx = 0.95andx =,9.96
4-93. l.et Xdenote th-e time u.ntil the first cou.nt. Tr.en. Xis an exponential 1<1ndom \'8tiab!e,~it!\ ,\ = ~ oo.:.nts per minute.
00 00

a) P(X > 0.5) = J 1e- 2xdx = - e- 2 xl = e- 1 = 0.3679

0.5
0.5
116 116
bl P[x< ~~] = J 1e- 'dx =-e- 2x l 2
0
= 1- e- 1!3 = 0.283 5
0

c) P(I < X < 2) =-e- 2

'1= e-
2

1
2
- e- 4 = 0.1170
 4-9'.5· Lct Xdenote the time t:ntil the first call. n.en. X iso:pooential and A = I = _I_ calls/ minute.
E(X) 15
a)
"" e-T.dx = - e-f; "" = e- 2 = 0. 1353
P(X > 30) = J-1
15 JO
30
b) The probability ofa t l ~st one call ina tO·mitmte intrn"SJ «!,lUlls one minu.s the probsbilityof 1.eroea1Js ina U)·mioute iotenosl and tf!.st is P{X > 10)

P(X > I 0) = - e --;; "" = e- 2'J = 0.5 134

10
n.erefore. t.l>.eanswer is l- 0 ,5l34 = O .t~8G6. Altcrnati\'dy, therea.ui:StOO: probabilityisf:<luaJ to P(X < 10) = 0486&
10
3
c) P( 5 < X < I0) = - e- u· = e- 1/ - e- 2'J = 0.203 1
5
X

d) P<>: o:) = 0:90 aocl P(X <X) = - e -t, = 1- e- x/ I S = 0.90.Therefore,>:= .34-54 minutes.
0

4-97. tet X d-enote tf!.e time to fai lt:re(in f!.ours)offans ioa personal oomp1:ter. Then. X is an o:ponential random \'Sriableand A = l/ E(X) = 0 .0003.

a)
P(X > 10,000) = J"' O.OOOJe- xo.ocoJdx = _ , - xo.oooJI"' = , -J = 0.0498
10.000 10.000

1.000 1.000
bl P(X < 7,000) = J O.OOOJe- xo.oooJd,· = - e- xo.oooJI = 1- e- 2·1 = 0.877 5
0 0

4-99. tet Xd-enote tf!.e timenntiJ the arrival ofa taxi. n.en. X is an exponential tana'om \'3riable,-rithA = l/ l£(>.1 = 0 .1a rrh>alsjminnte.

<" 00
Jo. ~e-0· "dx =-e-0· 1t
a) P(X > 60)=
&.1
0 = , - • = 0.002 5
10 10
b) P(X < 10)= J o. J,,- o.lxdx =-e- ·"1= 1- e- = 0.632 1 0 1
0
0

c) P(X > x) = J
00

o. ~e-0· 1 'di = _ , - o.. . l

..

X = . - O.Ix = 0.1 and X= 23.03 minmes.

X

d) P{X < >:) = 0 .9 implies tf!.st P(X > x) = 0.1. Therefore. this answer is tf!.esame as part c).
X

e) P(X < x) = - e- 0·1 '1 = 1- , -0.1> = 0.5 and x = 6.93 minmes.

0
4·101. tet X deootet lw! m:mber ofit'JS(!Cf fragments per gr<~m . Tlten
X-IU/{!44 / ~l

a) ::!2..5/ 144 = 15.fu..5

- Ad 14.4x28.35
b) P(X = 0) = .:..
" .,..:.".:... e 225 = 0.1629
0!
7 . -6
C) (0.1629) : JXlO
 4-103. tet Xdcootet he lifetime ofan assembly. Tltcn. X isano:pooeotiaJ NIOOom \ "ariable,,itttA = Jj l-;(X) = l/401) fil ilute$ per lt.our.
100 100
a) P(X < 100)= J4~0 e-x1400dx =-e-x1400 1
0
= 1- e- 0·25 = 0.22 12
0
00
b) P(X > 500) = - e-x/400I = e- 5I• = 0.2865
500
c) From the memoryless propertyofth.ef'Jipoo.."'tltial. t.t.isanswer is th.est~ m eas pan a .• P(X < 100) = 0 .2::!:1~L
d) tet U denote tl".e nll.mber o1 ass.embliesoll.t of 10 thst filii bclOre 100 ~.ours. By the memoryless property ofa Poisson prooi:SS, U f!.asa binomial distribll.tioo,vi t~ n = 10 and p = 0.2211
{from part {a)). Tlwn.

P(U ?. I)= 1- P(U = 0) = 1-[ ~O ]0.2212°(1- 0.2212)10 = 0.9 179

e) l.d v deootetlw! m:mber ofa.ss.emh!i eso~>t oflo ths t fail before Boo ~.ours. Tltcn. vis a binomial tilodom vsriablewitll n = u) aDd p = P(X < Boo). wlt.erf: Xdenotes t~ lifetime ofan
assembly.

800 800
Now, P(X < 800)= J -1-e- x 1400 dx =- e- xi400 = 1- , - 2 = 0.8647
0 400 0

Therefore, P(V = I0) = [: ~ ]0.8647 10 (1- 0.8647)0 = 0.2337

4·105. l.et Xdeoote th.c rmmher ofcalls in jO minutes. B«:ause the time bet\<.·eencaJis isanf'.Xpoo.."'tltial tilndom variable. X is a Poisson 1<1ndom variable,-rith.A = l/ 1-;(X) = 0 .1calls per minute
: JC.'t!ls per jO minutes.

- 3... 0 - 331 - 3... 2 - 3 ... 3

a) P(X > 3)= 1- P(X<3) =1- e J + <' + e J + e .> = 0.3528
0! I! 2! 3!

-3 ... 0
b) P(X = 0) = e .> = 0.04979
0!
c) l.ct Ydeoote the time bml.·eencalls in minutes.Then. JlY ~ x) = 0 .01 and

P(Y> x ) = J0.
00 "'
Je- 0· 1'dt = - e- 0.1' x = "- O.lx. Therefore, , - o.1x = 0.01 and x = 46.05 mimnes.
X

00 00

d) P(Y > 120) = J o. le- O.lydv=-e- 0·1Y = e- 12 = 6.14 x i0- 6 •

120
120
Because thee11Us area Poisson process. the numbers ofcaJis in disjoint inten>alsare independent. Ftom Exercise4-90 p;~rt b). the prob.!lbi!ityof no calls inooe:-hslt ~.oru ise- = 0.04979.
3
c)

Therefore. t!teanswe:r is [e- "3r e-= 12 = 6. )4 X J0-6.A!temath>ely, liN! answ-er is tf!..e probabilityof oocaJis in 1\~·o ~.ours. From part d)of this exercise, this ise-l.2.
() Beca.:sea Poisson process is memoryless. probabilities do not depend on ,,·lti:llt.er or oot inten'3lsareoons.ec:uti\'e.Tlt.;:refore. parts d) and e) have tltesameanswer.
 00 00

P(X > B) = J!,.,-•'

e
9dx = _ , - xte
e
= , -• = 0.3679
e

b) P(X > 28) = - e- x/9 "" = e- 2 = 0.1353

29

c) P(X > 38) = - e- x;e "" = e- 3 = 0.0498

39

d) n.eresultsdonot<iependonO.

4·109. Xisanexpooential random \'ariablewithp = 3-5 days.

a) P(X < 2) =
2
J_2_..
0
- x!l . Sdx = 1- e - 213. 5 =
3.5
0.435

00

b) P(X>7) = J~-xt3. 5dx = e-m 5 = 0. 135

? 3.)
-X/f!.S
c) RX>x)=0.9and:JV(>x)=e =0.9
Tlbetefore.x =- .'),sln(0.9 ) = Ojf>9.
d) From tbe JackofmemorypropertyP{X < 10 I X> j) = P(X < 7)andfrom p.llrt(b)ti'.i.sf.'qllals 1-0.13,5 = 0.86.;.

Sectlon4-9

4 ·lll. a) f{6) = .s!=l:!O

b) r [i) = l r[.1) = JJ.r[.l) = l.,.v2 = 1.32934

2 2 2 22 2 4

c) r[ 9 )= lr[l) = li3.ir[.l)= I05.,.•n = 11.63 17

2 2 2 22 22 2 16
4-113. a ) Th.e time until the tent"' call is an Erlsng random variable \'ittoA =.;calls per mirmte and: r = 10.
b) E(X) = l0/ 5 = 2 mint:t.-s. V{X) = 10/'.15 = 04 minctc.s.
c) Bcca~a Poisson process is memol)1e.ss. th.emeantimeis l/5 = 0 .2 minute.; or 1~seoonds
tetY deoote tlt.enu.mber ofcalls in one minute. Th.en, Y is a Poisson Nlodom variablewitlls calls per min~>tc.
,-ss•
d) P(Y = 4)= 0.1755
4!
- Ss O e -ss•
. e- ss?-
e) P(Y > 2) = I- P(Y < 2) = 1- e ; 0.8754
0 1! 2!
l.et Wdeoote the number ofone minute inten<~l.soct of 10 tha t oootaio more than::!. calls. Broiltse th.ec.allsarea Poisson process. W is a binomial tana'om \'3 riabl e,,i t~. n = 10 and p = 0 .87.;4.

n.<rclore. P( W = I0) = [: ~ ]0.87 5410 (1- 0.87 54)0 = 0.2643

 4·ll5. l.et X<teoote the time bctween failure.sofa laser. XisClo:ponentiaJ ""itha mean of ::;.:;.o oo.
a) Expected time until tl:eseoond (ai!l!.re: E(X) = J' 1 A=:!. 10.0 0004 = 50.000 ltom·s.
b) N = oooffaiJures io50000 hollJ'S

£(N) = 50000 2
25000
2)'
P(N ~ 1) = '£/ "(
? - ?
= 0.6767
k l
k=O •

4·U7. l.et Xdenote the nnmber o( bits t:ntil fiveerrorsocct:r. n.en. Xlt.ssan Erlang. distribt:tion,,ith r = 5 and A=10 -s error per bit.

a) E(X) = ~ = 5x 10 5 bits.
.A
b) V(X) = .!_= 5x 10 10 a nd ux = ) sx 1010 = 223607 bits.
.>-2
c) l.et Ydeoote IJ!£ number o( errors in u)5 bits. Then. Yis a Poisson rancf.om variable,,ilhA = 11105 = u) - 5 error per bit = ! error per 105 bits.

-110 +£..___+
-Ill e -11?1
P(Y ;,:: 3) =I- P(Y < 2) = I- e
! 0! I! 2!
- = 0.0803

4-119. a ) let Xdenote IJ!.e number ofcustomers that arri\'e in 10 milllit<S. Tlt.en. Xiss Poisson random \'S riab! e ,~ith
A = 0.:!-a nh-als per mint:te =:! arrh'lls per 10 minntes.

_??O _??I _??2 -2 31

P(X>J) =I- P(X<J) =I- e -- + " -- + " -- + " 2 = 0. 1429
- [ 0! I! 2! 3!
b) let Ydeootet.J!.<' m:.mber ofcustomers IJ!.atatri\'t in 15 mint:tes. Then. Yis a Poisson rancf.om variable,,ilhA = 3atrivals per 15 minutes.

- 330 - 331 - 3· 2 - 3·,3 - 3· 4]

P(Y ;::: 5) =1- P(Y~4) =1- e + " + " -' + " -' + " -' = 0.1847
[ 0! I! 2! 3! 4!

4·121. Jo
t'O

f(x;A,r)dx = Jo
oo Ar xr-1f!- >.x

r (r)
X . lety= At'.th-entludntegralis JA
oo

o
r-1 _ y
Y e !!f_. From tlt.eddinitionofr(•·).thisintcgr.aJisrccognizedtoequall.
r (r) •

4-1~. l.et Xdeoote the number of patientsarri\'t ttt the emergencydq>artment. n.en. Xh.ssa Poissondistribt:tion '~iti!:A = 6-5 patients per tt.ou.r.
a ) E(X)=ri A = 10 1 6-5 = 1-539~.ou.r.
b) l.etY deootetf!.e ncmberofpatients thstarrh't'in :!.0 minl!.tes. n£n. Yis a Poisson random \>ariablewithA. = 6-5/3 = 2.1667 a nh>als per :!.0 minl!.tes. Thee\'ent tltat tfte thirdanh'31o:ceeds
:!.0 minutes istqliivalent to tlteC\>er.t that t!t.creare t\\'OOT fewer arrivals in :!.0 minutes. Tttereforc.
. - 2.16672 16670 . -2.16672 16671 . - 2.1661? 166721
P(Y~ 1) = '
[ · +' · +' -· = 0.63 17
0! I! 21
Tile solution mayalso be obtained from tl:e rf:S-..!t that tlte time until tl:f! thirdatri\'31follows a gamma distribl!.tioowitn •· = jaod i. = 6-5 a rri\'lJs per hour. n.e probability isobtaioed by integra ting. the
probtlbilitydi!OS:ityfunction (rom :!.0 mir.11.tes to infinity.
S«:Uon+IO

£ (XJ = 10or [1 + -1]= IOOx5!= 12,ooo

0.2

0~2 ]- I00 [r[ I+ O~J

2
2 2 10
V(X) = I00 r[ I+ = 3.61x I0

4 ·12'7. l f X isa Wei bull Ntndom \ 'Sriable \'lith U= 1 and 6 = 1000. thedistribli.tionof X is theo:poo.-:ntia! distribt:tion \~i th ). = 0.()01.

0
/(x) = [- 1
1000 1000
][-
x] j ,:oo)'Jbrx >O

= 0.00 lc - O.OOix for x > 0

TJ>.emeaoofX is F.(X) = l/ A= 1000.

4·>'9 a) £(X) = or[I +~)= 900f (l+ I/3) = 900[(4 / 3) = 900(0.89298). = 803.68 hours
b) V(X)=o2r[l+~]-o2 r[l+_~f =9002 r[l+~]-9002 [r[l+ ~w
= 9002 (0.90274) - 900\0.89298) 2 = 853 I9.64 hours2

500J
[ 900
c) P(X < 500) = Px(500) =I- e = 0. I576

4-1 3 1. a) B= 2, l\ = 500

£(X) = 5oor [ 1+ ~] = 500f(L5J

= 500(0.5)[(0.5) = 250.{; = 443. I I
= 443. I I hours

b) 2
V(X) = 500 [(1 +1)- 500 [r[ I+
2
~w
= 5oo2 r (2) - soo2[f(L5)f = 53650.5

250)'
[ 500
c) P(X < 250) = F(250) = I- e = I - 0.7788 = 0.22 I2
 4- I 33. or[ I + .! ] =
2 2
Var(X) + (EX) = I0.3 + 4.9 = 34.3 I
2

or[I + .~ ]= E(X)= 10.3

Rcqdresa numuicaJ solntion to th.esi!: two tqiUitiom.

b) P(X > 6oOOi X> 3000) = P(X > 6000, X> 3000) = P(X > 6000)
P(X > 3000) P(X > 3000)
1- F (6000) " - (&JOCV4000)' 0. I054
= 1_ ~ (3000) = -e --(.,-
30.,-
0CV
.,-4.,-
00.,-
7
0) ' 0.5698
0. I850

c) If it is an exponential distribution, then 13 = I and

I- F (6000) e- (.oocv•ooo) 0.223 I

= X = = 0.4724
1- Fx (3000) e - CJOOCV4000J 0.4724

For the Wei bull distriblltioo {\\i t~ IS= ::!) tJ!.ere is oo Jsckofmcmorypropertyso th£t ttheans\~·ers to parts (a)and (b) di fter \''h.ereas tt.eywoul d be t~.esam e ifan exponential distrib~ttion ,,·ere assumed.
From part (b), f.t!.e probability ofsurviva l ~~mel 6000 lt.ours.gi\'eot.ede-.ict hasalr-eadys-.:rvh't'd3000 ~.ot:tS, is lower than the probability ofsurvival be)-ond$000 ~.ours from tbe start time.
-{3s00/2000)
4 ·1,37. a ) Jt\"> j.SOO) =l-FX (lsOO) =e =0.0468

b) Themesnoft~.is Weibull distrib.:tioni.s (2000) 0.5,J; = 1772.45.

r( it is an o:poo.."'OtiaI distri hl:ti_1is~MW'~~n then
ft\'> .',1.500) = 1-F.>.U ;OO ) = e = O.ljSH.
c) Tlte probability tf!.at f.t!~ lifetimeo:ceOOs j.SOO ~.ours is greater unrli!T tJ!.eo:pone:otiaJ distribution than under this Wei bull distribution model.

4·lJ9. a) Xisa logoonn.al distributionwitl\0=- :!and(l) =9. •

P(500 < X < I000) = P(500 < ew < I000) = P(ln(500) < W < ln(l 000))
= .P[ In( I O~O) + ]- .P[ In( SO~)+ ] = .P(2.97) - .P(2.74) = 0.0016
2 2

b) P(X < x) = P(err :o; x) = P(JV < IIl(x)) = .P[ln(x)+ ?- ] = 0.1

3
ln(x) + 2 28(3)- 2
- 1.28 x = e-1. = 0.0029
3
 05
a) P(X > I0) = P(e"' > I0) = P(W > In(I 0)) = 1- q,[ ln(I0) - · ]
1
= 1- q,(l.80) = 1-0.96407 = 0.03 593

b) P(X 5. x) = P(ew < x)= P(W < ln(x)) = .P[ln(x) - 0.5] = 0.)0
,
1

ln(x) - 0 ·5 0 x= ,o( J)+0.5 = 1.6 5 seconds

I

b) P(X > I0000)= P(ew > I0000) = P(W > In( I0000)) = 1- q,[ In (I OOOO) - 8.4056]
1.2686
= l-q,(0.63) = 1- 0.7357 = 0.2643

c) P(X > x) = P(ew > x )= P(W > ln(x)) = q, [ln(x) - 8.4056 ] = 0.1
1.2686

ln(x) - 8.4056 - 1.28 x = e -1 100( 1.2686)+8.4056 = 88 1. 65 hours

1.2686
2 X 2
4·14 5· tet X· N(lt,o ). then Y= e folio\~'Sa lognonnal distri b~tion,.,rifl!. meanpaod \'arianoeo . By definition.

Fy(y) = P( Y :S: y)= P(ex < y) = P(X < logy)= Fx(log y) = q,[ log:- f£ J.

s;""" Y= ,x sod X- N(l'.a\ wecansltow tl>at}~ (Y) = _!_ fx(log y)

v
8P (y) 8F .(log y) 1 . 1 I j~o'(."")'
Finally,fy(y) = Y = ' =-fx(log y )=-· .Jh' l · .
8y 8y y Y u 2rr
 5
P(X <8) = P(ew < 8) = P(W < ln(8)) = .P[l n(S) - 1. ] = .P(l .4486) = 0.9263
b)
0.4
c) IV<< o) = o for tl:e lognonnaJdistriba:tion.lftl:edistrihl'-tion is normal. th.en
4 855
P(X < 0) = P(Z < O- · ) = 0.008 .
../4.0898
Bec!luscwaiting times cannot be o.-:gath't the nonnal distribt:.ti ongmeN~ tessome modeling error.

section + u

0 25
4-1 49. a) P(X <0.25) = f. r(<> + .B) )x0 - 1(1- x)P-I
r (a)r (,B)
0

= j r(3.5) )xu = (2.5)(1.5)(0.5).[; .,.25 025 = 0.2525 = 0.03 13

0 r (2.5)r(l) (l.5X0.5)0); 2.5 0

b) P(0.25<X < 0.75) = J

o.•5 r
(<> +
o.25 r(a)r (,B)
f3
))x 0 - 1(1- x)"- 1

o•5 r us
= J r(3.5) ).,.u = (2.5Xl.5X0.5)\Irr x
25
= 0. 7 52s _ 0.252.5 = 0.4559
025 r (2 .S)r (l) (t.sxo.s}J,. 2.5 o.2s

c) p. = E(x ) = "' = 2.5 = 0. 7 14>

'
<> + {3 2.5+ l

"2 = V(X) = o,(3 = _ _::

2.:.:_5_ 0.0454
2
(a+ ,8 ) (a+{3 + 1) (3.5) 2 (4.5)
 <> -1 2
4-1 51. a) Mode = - - - - - - - = 0.8333
a +.B- 1 3 + 1.4 - 2

p. = E(X) = --=.
"- 3
--='---= 0.6818
<> + 13 3+ 1.4

,,Z = V(X) = . (\{3

42
' = 0.0402
2
(<> + .B i(a+ i3 + I) (4.4) (5.4)

<> -I 9
b) Mode = = 0.63 16
<> +.B - 2 10+ 6.25- 2
<> 10
f' = E(X ) = 0.6 154
<> + 13 10 + 6.25
2 = V(X) = <.¥3 62.5
(1 0.0137
(a + .B)2(<> + /3 + I) (16.25f( J7 .25)

c) Botltth.e meananch-sriance from part a)aregreatcr than for part b).

4·1$3. l.d X <ieootc tl:coompletion proporti onoft~.e maximum time. Tl:co:erciseoonsid.e:rs tl:c proportion'.!/ '.!.!) = 0.8

P(X>0.8) = J r(a + /3)_,.•-' (1 - x)~-c

I

0.8 r (a)f(/3)

I
2 3
= J' r (S) x(l - x)2 = (4)(J)f(J) [ x - 2x + x•] = 12(0.0833- 0.08 11) = 0.0272
0.8 f(2)f(3) f(2)r(J) 2 3 4 0.8

4- 155. a) P(X < 40) = P[z< 40 ~ 35 ]

= P(Z < 2.5)
= 0.993 79

b) P(X < 30) = P Z < 30- 35]

[ 2
= P(Z <- 2.5)
= 0.0062 1
0.62 1% are scrapped
 4-1 57. a) P(X > 90.3) + P(X < 89.7)

= P[z > 90.3 - 90.2 ] + P[z < 89.7- 90.2 ]

0.1 0.1
= P(Z > I)+ P(Z < - 5)
= 1- P(Z < I)+ P(Z < - 5)
= I - 0.84134 + 0
= 0. 15866.
Tlterefore. tJt.eans"'·cr is 1).15866.
b) n.e proress me.'lnsltould be set at th.ee.."tlter of the specifications: t~.at is. at#= <)0.0.

c) P(89.7 < X < 90.3)= p [89.7 - 90 <Z < 90.3 - 90]

0.1 0.1
= P(- 3 < Z < 3)=0.9973.
Tite yield is 100*0.9973 = 99.73%.

d) P(89.7 < X < 90.3) = ? [89.7- 90 <Z < 90.3 - 90]

0.1 0.1
= P(- 3 < Z < 3)
= 0.9973.
P(X = 10) = (0.9973 )10 = 0.9733

e) tet Ytep«'SCnt the numberofeastS outofthesample ofu) th£ttare f>ct\•·ren ~.7 and<)()~ mi.n .enYfollo\•-sa bioomiaJ distribntion"'itlln = u) andp = 0 .9973.Thu.s, E(}') = 9.973or u).

4 ·159· E{X) = 1000{0.:/) = :l-00 and V{X) = l000(0.2X0.8) = 160

a) P(X > 225) = P(X '2 226)~ 1- P[z < 225~200 l = 1- P(Z< 2.02) = 1-0.9783 = 0.0217

P(175 <X< 22 5) ""' P[ 174.5- 200 < Z < 225.5 - 200] = P(- 2.02< Z < 2.02)
b)
--- ..JI60 -- JJ60 --
= 0.97 83 - 0.0217 = .9566

c) lf P(X> x) = O.OI, then P [Z>xJ!toO ]= O.OI.

Therefore, 'Ji¥o
160
0 = 2.33 and x = 229.5
 4-161. let Xdenote the nt<.mberof calls inS ~.ou.rs. Because tlto: time b.."'\\.ox:ncalls is an exponential Nodom \oariab!e. tlw! m:mber ofcalls in;} hol!rs isa Poisson hlodom \oariab!e. t\o'"· th.e mean
timebef\~·eeneaJis is o,s ~.ours and A=1/0s = ~calls per tt.ou.r = 6calls in$ ~.ol!.rs.

P(X > 4) = I- P(X < 3) = I- e

- 6
6o + e- 6 6, + e- 6 62 + e- 6 6 3 I = 0.8488
- - 1 0! I! 2! 31

4 -16;}. tetXdeoote the lifctimc.

a) £ (XJ = 70or (l + ~)= 620.4

2 2 2
'?/ I' (X) =too 1l 2l-700 l ll> ~ ll
= 700 {1)-7oo (o.::;,s;r) = u)_;,t54:9

[620.4)'
700
c) P(X > 620.4) = e = 0.4559

2.5 [ 2 ]2.5
a) P(X<2.5) = J (O.Sx -l)dx = 0.5 ' - x = 0.0625
2
2 2

4 ? 4
b) P(X>J) = J (O.Sx - l)dx = 0.5x- - x = 0.75
J
2 J

3.5 2 3.5
c) P(2.5<X < 3.5)= f <O.Sx - l)cb· = O.SL - x = 0.5
2 25
2.5

X X ?
12
d) F(x )= J (O.St - l )dt = 0.5- - t = L - x + I. Then,
2 2 2 4

0, x <2
x2
F(x) = - - x+ l, 25 x < 4
4
I. 45 x

2 4
e) E(X) = J4 x(0.5x -l)dx = 0.5L • - L = 11- 8 - ( i- 2) = .!Q
2 J 22 3 3 3
4 4
V(X) = J (x - 'f J\0.5x - l)dx = J( x 2 - 2°x+ 100](0.5x - l)dx
2 2 3 9

2
'[ 3 9 9
'
= J 0.5xJ_ .L!.x2+l!.Q.x - 100 dx = L 4 - ll,,.l+ 55xz - IOOx 4
89 9 92
l
= 0.2222
 a)

b) Lct Wdeoote the ncmber ofCPUs that fa il "'it.f!.intfte next tllreeyears. Tlteo. W is a binomial random \'Sriable "'ith n = 10 and p = 0.$93.5 {from E.xercisc4·1.)0 ). Then.

•
so =e
8 6t .
S+1.i~l a) Fiod tlte'llh~3fOJM(,) giveo tft.:. t F.{X) =so andV{X) = 4000
41)00 =e {e -1)
.[; 1 21 2
letx =e andy=e tft.eo{l )SO = X Yand {~)4000= x y{J,'-l)= x y - x y.
50
Squ.are{l ) forx X = . { ; andsubs.tih!te into(~)

50
4000 = [ ;
2y 2 - [ [;
50 ]2
y= 2500(y - I)
[ ]
y = 2.6

50
st:bstiruteyba<:k in to(J)andsolvtfor x X = ~= 3 1.
• " 2.6
0= l otll ) =j~aod61 = ln{2.6) =0.91)

b) P(X < 150) = P(ew < 150) = P(W < ln(ISO)) = <I>[ ln(ISO) - 3.43]
0.98
= <P( I.6 1) = 0.946301

4-171. ld Xd-enote t~.d.eight ofa plant.

a) P(X > 2.25) = P[z > 2 · 2 ~~ 25 ] = P(Z > - 0.5) = I- P(Z < - 0.5) = 0.69 15

20 25 25
b) P(2.0 < X < 3.0) = P[ · - _ · < Z < J .O- · ] =P(- I < Z < I) = 0.683
0.) 0.5

c) P(X > x) = 0.90 = P[Z >x - ~.5] = 0.90and x- ~.5 = - 1.28.

0.) 0.)
 a) P(X > 5.5) = P Z > 5.5 - 5] = P(Z > 2.5) = 0. 0062
[ 0.2
45 5
b) P(4.5 < X < 5.5)= P [ · - < Z < 5·5 - 5 ] = P (- 2.5 < Z < 2 .5) = 0.9876
0.2 0.2
n neforc. th-e proportion ll'.at do not moo specific.'ltions is
1- P(4,s < X< .;,s) = 0 .0 12-.

b)
[ x-5
] x --
If P(X < x) = 0.95, then P Z > - - = 0 .95. Therefore, -
0.2 0.2
5 = 1.65 and x = 5.33.

4·!7.5· {(P{0.002 - X< X< 0 .00:!.- X), t.f!..eo P(- X/0.000 4 < Z < xj0.00CJ4) = 0 .99Jj.. n .erefote,xj0.0004 = j and:x = 0 .0(H2.. n .esp!lcific.'ltionsare from 0 .000 8toO.OOj.~.

5800 J 7000
5800)
J-7000
X
1
a) P(X < 5800) = - e ?OOOdx = I- c -l = 0.5633
0

X X

J7 ~00
00

b) P(X > x) = e ?OOOdx = 0.9 Therefore, e 7000 = 0.9 and x = - 70001n(0.9)= 737.5 hours.
X

4-179. a ) Using tl:e normal approximation to t~.e bioomial ,.,;tn n = .:;o•j6.j6 = 64.800.and p = O.OO()l wt: Ita\'€:: E(X) = 64800(0.0001) = 648

P(X > I) ""

- -
p[ X - np
Jnp(l- p)
> 0.5 - 6.48
J64800(0.000I):0.9999)
l
= P(Z > - 2.35) =I- 0.0094 = 0.9906

b)
P(X > 4) "'
- -
p[ X - np > 3.5- 6.48
)np(l- p) - )64800(0.0001X0.9999)
l
= P(Z '2 - 1.1 7) = I- 0. I2 I0 = 0.8790

4-181. a) P{X> x ) implie; that there are r - 1or lessoollllt$ in an intenoaJof length x. l.et \'denotethe numberofooc.nts in an intc:nosl of! engt~x . T~""ll. Yis a Poisson ~<~ndom \'arisble ,.,; ,~
psrameterAx.
r -1
Then.P(X> x) = P(Y 5 r - I) = L "-.lx (~)'.
1=0
1'-1
b) P(X < x) =I- L "-.lx (~?
f= O

,._, I," I' ,._, I>.x\')' (:..,·)'-'

c) f, (x) = ..iL F (x) = ;.., -xx"'r:::.L_- ,-"'"' Afr:::.L = >.e-.lx.L._L-
~ * X ~
i= O
.,
I .
~
f= O
.,
I .
(r - I) .'
 • • •
4·l8j. a) Q-uality loss= £k{X- m) = kE(X- m) = ko , byth.edcllnitionofth.e,'tlriance.
b) Qusl ; tyk==~-m) =kEIX-#"#-m) • •
= kEI(X- "!"(jl- m) •" o(jl- m)(X- #ll
:d:.E(X- p) - A"(p- m) - !!J.'f#l-m}}-;{X- p).
Tlbe last term oqu:alszero by t!tedefiniti~nof the me.'ln.
2
Therefore.qu.slity loss=ko .o.k(p:-m) .

P(t1 < X < t 1 + t2 )

4·18..;. P( X <t 1 + t., IX > t 1) = from thedelinitionotoooditionaJ probability. Now,
- P(X > t 1)

+•! ',+s~
P(t < X < t + t ) =
1 1 2
J
t1
>..e-"'dx =-e- >.x
1
= e- /.1• - e- '-(1,- l,)
', '
P(X >t 1) = - e- >.x - /.1
=e *
I,

- AI
1- e ' = P(X < t2) •