Let A represent bolts with diameters less than 8

event (A) = [4,6]

Let B be the event of nuts with diameters larger than 10
Event (B) = [12,14]
Let event c be choosing a bolt and a nut with same diameter
Event (C) = [(6,6) 1 (10,10]
 5
Example :
people stand in line in a movie theater

In How
=>
many
different ways they can be
arranged ?

5 Y =3 2 1 =
120 = 5
.

-
Number of permutions of objects is
!

Example 5 lifeguard are available for only on Suterday There

3 stations In how different ways life
are avaliable
many gards
can be
arranged stations
among .
51

=
.

5 + ya 3 60 15-3) !
ways
=

↑
Number of premutation of K objects chosen out of n objects

is n !
(n - k) !

* Example 5 lifeguard, 3 lifeguard

-
3 Station
2
5 ! = 5 + y + 32! = 10
-

(2) ! 3 ! 2dz(-2
/ !)

*
The number of combinations of K chosen from
objects
is n!
n objects
(n 1) ! -
KI
.
 -> Addition Rule UTO And
P (AUB) =
P(A) + P(B) -
P(AnB)

->
If A and B are mutually Exclusive , then :

P(AUB) =
P(A) + P(B)

*
P(too short or too thick) =
P(too short U too thick)
=>
P(oo short) +P(too thick) -
Pltoo Short And too thick)

10 + 3 + 5 +
5 + 4+ 3 5 035
= 0
-
.

100 0 1000 1000

* conditional probability

P(A(B) P(AnB)
Probability of A again B
=

P(B)
* P(Diameter ok given
that
length ok

ok OK

=
P (Diameter & length) =
900 1000 =0 95 .

(38 + 900 + 4)1 000

↑ (length ok)

and thick)
*
Prob (too long / too thick) =
P (too long too =

↑ (too thick)
= 13/1000 =
0 . 59

(5 +u + 3)/7000

* P(too long) = 0 .
04

* P (too long / too thin) =

2/1000 = o . 01

(10 + 38 +2)/1000
* A and B are two independent events

-> condition

P(A/B) = P(A)
PLB/A) = P(B)
Example :
A population of 600 semiconductors with items
coming from
3 lots A , Band C An item is chosen
randomly to check diameter

specification

lot confirming Non-confirming

A 88 12

B 165 35

C 260 Ug

·
find P (lot A confirming) = P(lot Al comfirming = 88/600
P (conf) (88+ 165 260)/600 +

Coming from lot A knowing that conf 177

given it is 0
= .

->

·
P(conf/Lot A) = 881600 = 0 . 88

(88+ 12)/600

·
P (Not from lotc conf =
p(Notc conf) =
(88 + 165)/600
P(conf) (88 + 165 + 260/600

P(conf Not from let() = (88 + 165)/600

0 .
5

* P(Not() = P(c)'
=
1 -
P(c) =
1 -

260 + 40 = 06
600
3) write probmass function of X

X P(X(x)
O 49 %

T 39 %

12 %
2
1 %
3
 ·

Example

E
f(x) = 1 . 25(1 - x34 ,
02x47

O , otherwise

Zero 1 .
25(1 -
xy zero

- S ↓ ! &

up(x20 .
8) =

0
9 f(x)dx
.
8 0 . 5
dis
=1 25( x4)dx- -

+ ze

2)p(x(0 . 5) =
f f(x)dX

o
-
S
.5
0

=Jf(x . ax +
S
O
f(xdx = 2x -
x

3) Commulative Dist fun

-
&
2
f(x)dx = 100 % = 1

1 &
G

T
S f(x) dx +
f f(x)dx +
S f x)dx
1
-
L

zero + 1 . 2501-x4) + zero

0 + 1 + 0 = 1
3) Mean

x-m.
S x f(x)dx
=gx( .

29( -
x4) .
dx

5) Variance

fixe
 Chapter 4 : Commonly used Distributions

· Discrete Random variable

1) Binomial Dist
2) Poisson Dist
·
Continous Random variable
1) Normal Dist
2) Exponential Dist
3) uniform Dist

>
Binomial Dist : Bernonli experiment: with only two possible out comes

n : number of trials > number of success

P : Prob of success >

X- Bin (n , p) - Parameters
follow s prob . mass function

(xi(
+
x pr - T,x
x))4
-
= 0, . . .
n

P(x x)=
= -

,
other wise
O
 Wed 13 Des
->
Discrete R V .

1) Bionomial Dist -
Bernouli 2 possible outcomes
-
Xw Bin(n p), > prob
mass function ,

[Bionomial -table]

> Continous R-V

Bionomial Dist
Mean =n .

p
variance = np(1 p) -

Example:
Xu Bin (6 ,
0 .

6) find
1) Mean = 6 (0 6) .
6 = 3 .

2) S D .
=
6(0 6) (0 4)
.
.
= 1 44
.

-
S D .
=
Stun
3)p(x = 4) = 0 . 399
u(p(X - 6) = 1 -

p(x(6) = 1 -
0 .
047 =
0 . 95

2) poisson Distribution
ms Discrete
X poisson (2) Mean =↑

Aug/Mean/Rate - Sth percentage variance = ↑

[
Q
P(X X) ex
theinteger
-

=
C &

,
X

XI

O , other wise
find the area under the curve between z1 = 1 . 28 zz =
0 . 77

p(z(1
P(2<0 71)
.
28)
:
=

=
0
8997
.

0 7611 .
-
71<z41 28)
p(0 . .

0 .
71 1 28
.

71)
p(z<1 28) p(z 0
- -
.
.

=
0 .
8997 -
0 . 76
=
0 . 1386

Example lifetime of battery is normally distributed M 50hrs/S D=5hrs = .

find the prob of chosen one is btw 42 and 52

X - N(50 , 5) p(42<x(52)
p(4z0 <2 <52 50) -

S
=
p(64z(ou)

p(z(0 4) 1 6)
p(z) 0 6554 0 5480 0 1074
. -
-
. = . -
.
= .

Diameter is normally distributed M =

2 .
505 S D . =
0 . 008

specifications btween 2 . 5 70 . 01

↑ (2 49<x(2 51) p(-1 884740 63) =

0 7357 0 03
· -
.
.

<
. .

= 0-7056

Example
CmN(40 , 1)
F =
1 8C + 32
.

-
find distribution of f

-> N (1 8(40) +32 .

,
1 8 (7)
.
 Example
C-N(150 , 30)
N (200 , 60)
-

Our (1500 , 100)

E =
2 + 3 5N
. + o

e S 19.

E -

N((2(150) + 3 5(2007
.
+
1500 [2(30) ,
+ 3 .
5(60) +
100)
22 (301
2
Variance (E) = + (3 5) 2(6012
. + 110012

P(z<2 .
08) = 1 -

p(z2 . 08)
1 -
0 . 9812 =

Exponential Dist Time elapes before an event (waiting Time)

life time

E
xm Exp(x) 1 - ex ,
Xo Mx =
1/X
Communative Dist function O ,
otherwise SY =
Y*
+p(X(x)

Example X-Exp(u) ,
find Mx ,
Sx , p(X(0 .
2)

Sx
-
ux
= =

4
- TX 4(0 2).

off partically
#
p(X(0 1 X poisson (15)
->
.
2) = 1 -
e = - =

yu
p(T - bs]
M Tw Exp(a)
Example Radio active mass emitt particules with mean of
particles 15

find the prob thatI see will pass before the nextemission
per min

25(4)7
- 0 .

p(T >) 1 p(+ (b) 1 C 2865

=
= -

= -
-
e 0 .
 X Y
Example
5 8 7 .
8
5 85 . 7 r = 0 .
988
5 - 6
83

0 .
05 48 3 .

0 05
51
.

0 . 05 54 .
7

2 63 -
2

2 67 .
8

2 66 . 2

Regression Estimates the best

:
straight line that summarise the
Relationship between X , Y

y = a + bx

1)b =
S(x -
x)(y -

j)
2(X -
y)z

2)a =
y -