0% found this document useful (0 votes)
54 views8 pages

Probability Cheat Sheet

1) Two events A and B are independent if the probability of their intersection is equal to the product of their individual probabilities. In other words, the occurrence of one event does not impact the probability of the other event occurring. 2) Mutually exclusive events cannot occur at the same time. The probability of their union is equal to the sum of their individual probabilities minus their intersection probability. 3) A discrete random variable can only take on countable number of values, unlike a continuous random variable which can take any real number value. The probability mass function defines the probability of each value the discrete random variable can take.

Uploaded by

Bridget Nguyen
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
54 views8 pages

Probability Cheat Sheet

1) Two events A and B are independent if the probability of their intersection is equal to the product of their individual probabilities. In other words, the occurrence of one event does not impact the probability of the other event occurring. 2) Mutually exclusive events cannot occur at the same time. The probability of their union is equal to the sum of their individual probabilities minus their intersection probability. 3) A discrete random variable can only take on countable number of values, unlike a continuous random variable which can take any real number value. The probability mass function defines the probability of each value the discrete random variable can take.

Uploaded by

Bridget Nguyen
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

Probability Independent events

no times A occurs n (A)



A & B are independent when :
p, (a) Pr (An B) PRCA ) Pr (B)
.

= = ↳ = ✗
no .
of trials n (E)
↳ Pr IAIB ) = Pr (A)
Pr ( A ) ) PRCA ) Pr (A) (B)
'
Pr / A Pr (A) does not affect
'
: I -
(=) = I - .
Pr

Pr (A)
Pr 10 ) = 0
; Pr (E) = 1 ;
Of c- 1 Venn
diagram
Additional rules :Pr ( AUB ) -
- Pr (A) + Pr (B) -
Pr CAN B) A B A B

only a
only
A not and B not

mutually exclusive : events can't occur at the same time B


B a

↳ Pr / An B) = 0
not AnorB
↳ Pr / AU B) = Pr (A) +
Pr (B)
Pr / AUB )
A B → Events A & B don't

have outcomes in
any
A A B
common B

⇒ A & Bare
mutually
exclusive events

conditional Probability
Pr ( An B) Complement of ACA
'
) mutually Exclusive
Pr 1A B) = , Prl B) =/ 0
pr (B)
TWO -
WAY TABLE / KARNAUGHMAP MULTI -
STAGE events
WITH Replacement
A
A A
'
E ¥
B AMB A' AB B § A
¥ B
A'
' ' '
B '
AND AB B

E A A
'
1
5 4 A
g-
g
B
Pr / AAB ) PRIAAB )=Pr( A)
'
+

¥ B
PRCA 'nB)tPr(A 'nB ) : PRCA )
' '

WITHOUT Replacement
3 A
Pr / An B) tprla 'nB)=PrCB ) I

pr( ANB )+pr( A 'nB )=Pr( B )


' ' '
§ A
I
8 B

5 4- A
8
Ty
B
4

J B
Discrete Random Variables
Discrete Random variable is one that can take -
median : middle value of distribution
only countable number of values .( do not have ↳
adding up prob until it's > 0.5

to take whole number ) -


GO.at 0.25 = 0.65

(⇒ mean : 1
Pr ( ✗ x ) (K ) :
=
=p

plx ) e
Of 1 , for all x .
Mode : variable has highest probability

¥ plk ) 1 = ↳ 0-4 is the highest
⇐ 0 is the mode
£
Pr / at i. b) =
aacsb plz )

Variance Var ( X) : how far away the ✗ values

Measures of Centre are from the mean


'
✗ 0 1 2 3 ↳ var ( x ) = El ✗ 2) -
( ECX) )
↳ Var lax + b) = a
'
Var ( X )
Prcx :X) 0.4 0.25 0.05 0.3
. Mean : Expected value ECN.ir aka .

average
-
standard deviation sdlx) ( o )
PRIX ) sd ( X ) Farci )
↳ Eliel =
adding up all ✗ ✗ ↳ =

'
↳ Elk ) : 0×0.4 -1 1×0.25 + 2×0.05 + 3×0.3 (⇒ (Sdk ) ) = Var ( X )
= 1.25 ↳ In general , for many random variables
4 E- ( ax b) + a E- (X ) + b Prt m 2 of x en -120 ) I. 0.95
-

↳ E- ( god ) =
adding up all glut ✗ PRIX)
Binomial Distribution
General Rule ✗ ~Bi In , p ) " "
Tech -

free technique
-
n: number of trial Prlx > 1) 70.95
-

p: probability of success 1- Prlx :o) > 0.95

" Pr (11--0) < 0.05

(F)
"

Pr ( ✗ = x) =
p
"
( l -

P) ,x= 0,1 , . . .
, n 0.52
"
< 0-05
0.05
! n
loge 0.52 <
loge
where (F) =
Ncp =
× ! (n
n

-
x) ! n >
loge 0.05
0.52
= 4-58
Loge
Es n = 5 .

Graph , variance , expected value


Biln , p )
✗ n
Using spreadsheet CAS
↳ Expected value : Eu) :
np
↳ Variance : Varix )= npcl p ) -

↳ standard deviation : sdlx) :O = Var ( X )

Finding sample space


✗ ~ Bi (n , 0.48)

Define → Trial & Error


Define f.lk/=binomialCDfl2 ,
K ,
K ,
0.48 )

-
sub different values for x
Continuous Variable
Continuous Random Variable : can take on . mis the median where
values that range over an interval of real values Pr ( Xfm ) =
2- = PRIX >m )

probability density funtion it is usually given :



E. g) Probability Density Function

by hybrid / piecewise function f. (x )


a

conditions
o
glx ) 30
y(x) :{ I -
sin 12711

0 ,
elsewhere
, k - I < x < k

°
1% fix)dx = 1 where 1 < k 24

Calculations
*
Notes : Prca < x ) = Pr (atx ) To find K :
Pr lack < b) lab fluidic K

%
• =

. Pr ( ✗ = a) = Sad glxldk = Flat -


Flat = 0 solve ,
I -
sin 12×10111=1 lake 4
co

. Mean : ECX) : f- as x -

flxldx ⇐, K: 1T¥ or
k=d"z
is

'
Var ( X ) = f. •
K
' -

ylk ) die -

µ
'

-
sdcx ) = Varcx )

m is

• median = f- •
Kiddie =/ m flxldx =
f-
Normal Distribution
Normal Distribution
: a
perfectly symmetric
continuous random variable defined by the Bell Curve Exact value of Normal Distribution
Pr within 10

General Rules ✗ ~
N ( µ 02) ,
'
Pr ( n -
o < x <
u to ) = 0.68
meat ↳ variance / Gda )]
Pr ( -1 C Z C 1) = 0.68
. Area under entire curve is 1 Pr within 20

.
Mean : E- ( X ) = u Pr (n -
20 < x <
µ -1 201=0.95
.
Variance : Var (X ) = o
'
Pr f -
2 < 2 < 2) = 0 95 .

.
Standard deviation : sell ✗ 1=0 Pr within 30
U -
o it µ to

Pr (µ -
30 < a <
µ -1301=0.997
Standard Normal Distribution : Z -
N lo , 1) Pr C- 3<2 < 3) = 0.997
-
Pr ( 2 2) + Pr ( 2 > 2) 1
< = Inverse Normal + CAS techniques
. Pr ( 2 < 2) = Pr ( 2 > 2)
-
Inverse Normal Normal Cbf
.
Pr ( 2 > 0 ) : 0.5
.
Pr ( a < 2 < b) Pr ( 2 < b) = -
Pr ( 2 < a)

Transform to / from Standard Normal Distribution

X -
U
z =
V ; K = Oz +
µ

Pr ( a ex < b) where
a = lower ; b =
upper
Sampling and Estimation
p
Sample distribution of Proportion for Binomial

Sample is a subset
of population Pr la c Ñ < b = Pr ( na e ✗ < n b)
p
.

.
Pr I Ñ > a) = Pr ( X > na )
.
Mean : ECÑ ) = Eth ) =
In ECX) =
ntnp =p
Population Proportion population : is a setof eligible
all In short : ECM =p
'
numbers of a
group It has
. a fixed probability .
Variance : Var (F) = Var (¥ ) =
#) var (X )

number of the attribute


=
÷ np ( I p )
-
=
PILI
p =
total size
( fixed ) In short : var (B) =
P"_¥
. Standard deviation : sd (B) = Var (D)
" P'
Sample proportion sample proportion is the sdlri ) =P
-

: ratio
n

of successful outcomes to the sample size


number of sample with attribute
Random sample size
p = ( Variable )
sample size
Main →
Keyboard →
catalogue → R → Rand List

p^ can be used as an estimate of p (n , start ,


end ) CAS techniques
• n = Sample size randy :
get a random no

Ñ
.

=
¥ where ✗ is a binomial random variable . start ,
end = domain rand ( range) get
: a random no

in the given range


→ Ñ c- ( 0 , In %
, ,
- - -

, ¥ 1) , randlistl domain ) get :


"
domain '

random numbers
Sample distribution of Proportion for Normal for : a confidence Intervals

sufficiently large sample size the distribution is


,

PY
ri
"n-Ñ) krill
-

approximately normally distributed . CI :( pi -


k , pit n
F- Nlu 04 ,

EIB ) =p Ñlhpj
Mean : k :
margin of error
Pll p) n
-

Variance : var ( ✗ > =


n
P"
-
Ñ
ri " PY
standard deviation : sdlx ) = 95% CI : K 1.96 ; CI c- (p -1.96
Blinn
-

:
, pi -11.96
n
n

i. Ñn Nlp , P''n) 90% CI : K : 1.64 ; CI c- (p -1.64


till B)
n
-

, pi -11.64
ri " PY
n
-

Probabily tips 99% CI : K 2.58 ; CI c- (pi ri " PY


I)
P' "
-

: - 2.58
n
, B -12.58

Population vs Sample small sample ( DISTRIBUTION TABU ) LARGE SAMPLE ( GRAPH )

SMALL population PROBABILITY TREE WITH WITHOUT Replacement

COUNTING METHODS WITHOUT Replacement

BINOMIAL WITH Replacement

HYPERGEOMETRIC WITHOUT Replacement

IRGE Population Binomial DISTRIBUTION NORMAL DISTRIBUTION


PDF

You might also like