3. Random Experiments
Sample space is the set of all possible outcomes
of a random experiment.
Sample point is each outcome in a sample
space.
Outcome is an element of a sample space.
Event is a subset of a sample space.
Probability is a number that is assigned to each
member of a collection of events from a random
experiment.
3
4. Axioms of Probability
If S is the sample space and E is any event in a
random experiment, probability satisfies the
following properties:
(1) P(S) = 1
(2) 0 < P(E) < 1
(3) P(E1 E2) = P(E1) + P(E2) - P(E1 E2)
(4) P(E1 | E2) = P(E1 E2) / P(E2)
4
5. Random Variable
Random variable is a function that assigns a real
number to each outcome in the sample space of a
random experiment.
Random variable is denoted by an uppercase letter, such as X.
After an experiment is conducted, the measured value of the
random variable is denoted by a lowercase letter, such as x.
A discrete random variable is a random variable with an interval
(either finite or infinite) of natural number (or non-negative integers), N,
for its range.
A continuous random variable is a random variable with an interval
(either finite or infinite) of real numbers, R, for its range.
5
6. Probability Distribution
Probability distribution of a random variable X is a
description of the probabilities associated with the
possible values of X.
Probability mass function of a discrete random variable
X, denoted as p(x)
Probability density function of a continuous random
variable X, denoted as f(x)
Cumulative distribution function of a discrete or
continuous random variable X, denoted as F(x)
6
7. The Law of Large Number
(weak)
Let X1, X2, ... , Xn be a sequence of n independent
and identically distributed (i.i.d.) random variables
with a finite expected value E(Xi) = < .
Then, for any > 0,
7
0
lim
X
P
n
8. The Law of Large Number
(strong)
Let X1, X2, ... , Xn be a sequence of n independent
and identically distributed (i.i.d.) random variables
with a finite expected value E(Xi) = <
Let also
Mn
8
n
X
X
X
M n
n
2
1
9. The Central Limit Theorem
Let X1, X2, ... , Xn be independent and identically
distributed (i.i.d.) random variables with expected
value E(Xi) = < and 0 < V(Xi) = 2 <
Then, the random variable
converges in distribution to the standard normal
random variable as n goes to infinity (n ), that is
where (x) is the standard normal CDF
9
2
2
1
n
n
X
X
X
n
X
Z n
n
Real
all
for
lim
x
x
x
Z
P n
n
10. Cochran’s Theorem
Let Zi be normally and independently distributed
NID(0,1) with parameter = 0 dan = 1,
for i = 1,2,...,. and
where s < and Qi has i degrees of freedom (i =
1,2,...,s). Maka Q1, Q2,..., Qs are independent
chi-square variables with 1, 2,..., s degrees of
freedom, respectively, if and only if
s
i
i Q
Q
Q
Z
...
2
1
1
2
s
...
2
1
10
13. Normal Distribution
Normal distribution or Gaussian distribution is a
probability distribution function of continuous
random variable X that has a symmetrical bell-
shaped curve. Most of the observations cluster
around the central peak and the probabilities for
values further away from the mean taper off equally
in both directions. Extreme values in both tails of the
distribution are similarly unlikely.
Random variable is an interval infinite of real
number from negative infinite - to infinite (), X{-
<x<}.
13
14. Normal Distribution
Penerapan Distribusi Normal antara lain
untuk menunjukkan sebaran data hasil
pengukuran ilmiah baik observasi ataupun
eksperimen, sebaran kesalahan, sebaran
rata-rata data subgrup, sebaran data yang
sangat banyak (Law of Large Number dan
Central Limit Theorem).
14
15. Normal Distribution
Parameter (mean) dan (standard deviation)
Probability Density Function, f(x)
Cummulative Distribution Function, F(x)
2
)
2
/(
)
(
.
2
)
(
2
2
x
e
x
f
x
di
i
f
x
F )
(
)
(
15
17. Standardized Normal Distribution
Standardized Normal Distribution is
normal distribution with parameter = 0 and
= 1
Standardized Normal Distribution is also
called by Z Distribution.
17
18. Standardized Normal Distribution
Parameter (mean) dan (standard deviation)
Probability Density Function, f(x)
Cummulative Distribution Function, F(x)
2
)
(
2
/
2
x
e
x
f
x
di
i
f
x
F )
(
)
(
18
20. Student’s t Distribution
Distribusi Student’s t adalah sebaran
variabel acak yang merupakan model
gabungan variabel acak X berdistribusi
Standard Normal yang mempunyai
parameter =0 dan =1 dengan variabel
acak Y berdistribusi Chi square dengan
derajat bebas sebesar yang mempunyai
parameter =/2 dan =2.
Y
X
20
21. Student’s t Distribution
Parameter (degree of freedom)
Probability Density Function, f(x)
Cummulative Distribution Function, F(x)
2
1
2
2
2
1
1
)
(
x
x
f
x
di
i
f
x
F )
(
)
(
21
23. Chi-Square Distribution
Parameter (degree of freedom)
Probability Density Function, f(x)
Cummulative Distribution Function, F(x)
0
)
(
0
0
)
(
0
x
di
i
f
x
x
F
x
other
x
e
x
x
f
x
0
0
)
(
2
)
( 2
2
/
1
)
2
/
(
2
/
)
1
(
1
)
(
0
1
dx
e
x x
23
27. Binomial Distribution
Parameter p (probability of success) dan n (number of
trials)
Probability Mass Function, p(x)
Cummulative Distribution Function, F(x)
other
n
x
p
p
x
n
x
p
x
n
x
0
,...,
1
,
0
)
1
(
)
(
0
)
(
0
0
)
(
0
x
i
p
x
x
F
x
i
27
30. Hubungan Distribusi
Hubungan Distribusi Standard
(Standardized) Normal dengan Distribusi
Normal
Jika X adalah variabel acak independen
berdistribusi Normal (,), maka adalah
variabel acak berdistribusi Standard Normal
X
Z
30
31. Hubungan Distribusi
Hubungan Distribusi Student’s t dengan
Distribusi Standard (Standardized) Normal
Jika X adalah variabel acak independen
berdistribusi Normal (=0,=1), dan Y adalah
variabel acak independen berdistribusi Chi
square dengan derajat kebebasan sebesar
maka adalah variabel acak berdistribusi
Student’s t yang mempunyai parameter =/2
dan =2
Y
X
31
32. Hubungan Distribusi
Hubungan Distribusi Chi Square dengan
Distribusi Normal
Jika X adalah variabel acak independen
berdistribusi Normal (,) dengan derajat
kebebasan sebesar , maka X2 adalah variabel
acak berdistribusi Chi Square
32
33. Hubungan Distribusi
Hubungan Distribusi F dengan Distribusi
Chi Square
Jika X1 dan X2 adalah variabel acak independen
berdistribusi Chi-Square dengan derajat
kebebasan sebesar 1 dan 2, maka rasio X1
dan X2 adalah variabel acak berdistribusi F
2
2
1
1
X
X
F
33
34. Hubungan Distribusi
Hubungan Distribusi Binomial dengan
Distribusi Normal
Jika X adalah variabel acak independen
berdistribusi Binomial dengan parameter n
(sangat besar, n) dan p (sangat kecil, n0),
maka X dapat diaproksimasi sebagai variabel
acak berdistribusi Normal dengan parameter
=np dan =np(1-p)
34
35. Hubungan Distribusi
Standardized
Normal Dist.
Z
Normal Dist.
N(,)
Student t Dist.
t(n)
Chi-Square
Dist.
2(n)
Fisher F Dist.
F(n1,n2)
X-
.X+
n=
Xi
2
X- 2
( )
X1/n1
X2/n2
n1.X1
n2=
Binomial Dist.
Bin(n,p)
=np
=np(1-p)
35
43. Kekeliruan dalam Analisa
Statistik
Galat tipe 1 (type I error, ) : kesalahan
menyimpulkan karena menolak hipotesa yang semestinya
diterima
Galat tipe 2 (type II error, ) : kesalahan
menyimpulkan karena menerima hipotesa yang
semestinya ditolak
43
44. Uji Hipotesa Rata-Rata, Variansi
Diketahui
Uji satu rata-rata, variansi populasi (2) diketahui
44
45. Uji Hipotesa Rata-Rata, Variansi
Diketahui
Uji dua rata-rata, variansi populasi diketahui
45
61. Analysis Of Variance
Model dasar ANOVA (analysis of variance) dari
eksperimen satu faktor tunggal dengan a level
perlakuan dan n replikasi
di mana
= Rata-rata keseluruhan
i = Efek perlakuan ke-i
ij = Kesalahan eksperimen perlakuan ke-i replikasi ke-j
n
j
a
i
y ij
i
ij
,...,
2
,
1
,...,
2
,
1
61
62. Analysis Of Variance
disebut effect model
jika , maka
disebut mean model
Regression model dapat dipergunakan
ij
i
ij
y
i
i
ij
i
ij
y
62
63. Analysis Of Variance
Total variabilitas diukur dari Jumlah Kuadrat
Keseluruhan (Total Sum of Squares, SST)
E
Treatments
a
i
n
j
i
ij
a
i
i
a
i
n
j
i
ij
i
a
i
n
j
ij
T
SS
SS
y
y
y
y
n
y
y
y
y
y
y
SS
1 1
2
.
1
2
..
.
1 1
2
.
..
.
1 1
2
a
i
i
Treatments y
y
n
SS
1
2
..
.
a
i
n
j
i
ij
E y
y
SS
1 1
2
.
63
64. Analysis Of Variance
Rata-rata Kuadrat (Mean Squares, MS) dihitung
dari Jumlah Kuadrat (Sum of Squares, SS) dibagi
dengan derajat kebebasan (degree of freedom,
atau df) masing-masing
1
an
SS
MS T
T
1
a
SS
MS Treatments
Treatments
)
1
(
n
a
SS
MS E
E
64
65. Analysis Of Variance
65
a
i
n
j
ij
T y
y
SS
1 1
2
..
a
i
i
Treatment y
y
n
SS
1
2
..
.
Treatment
T
E SS
SS
SS
H0 ditolak atau antar perlakuan pada faktor
memberikan efek signifikan jika :
)
1
(
,
1
,
0
n
a
a
F
F