. .

. .
MSc (..../ )
Team Site: A.E.A.C. Co. Project Manager-Site Administrator
e-mail: s_4goum@[Link] , My Blog.
16/07/2011

.
. /


.

.
.

.
.

1)
2) ( , ,
),
. 3)
. 4)
/
.



.
. 1) 2) .
) ) 3) .
.
[,].
. 1) (0,1,2,3, ), 2) (0%,
10%, 30%, 40%).
. , 2.5 .
( ) 10.78%.
.
[,].
b

P ( a < x < b) = f ( x)dx

a

. 1) (15, 50, 60 ), 2) (1.75, 1.80, 1.90 ).

. ,
20 2 , 35 5 4 .
1.76, 1.77, 1.80 4
( ).
(-,+).
().
[,]
( ).
x> x->0, .

Easy Fit 5.1
excel. Easy Fit 5.1 50 ,
. ,

.


.

4 .
Easy Fit 5.1
.

Easy Fit 5.1.

: Beta, Johnson SB, Kumaraswamy, Pert, Power Function,
Reciprocal, Triangular, Uniform,
: Cauchy, Error, Gumbel Max Gumbel Min, Hyperbolic
Secant, Johnson SU, Laplace (Double Exponential), Logistic, Normal, t-Student
Burr, Levy, Gamma, Inverse Gaussian, F Distribution,
Fatigue

Life

(Birnbaum-Saunders),

Frechet,

Chi-Squared,

Dagum,

Erlang,

Exponential, Weibull, Rice, Rayleigh, Pearson, Pareto, Nakagami, Lognormal,

Log-Logistic, Log-Gamma.
: Bernoulli, Binomial Discrete Uniform, Geometric, Hypergeometric,
Logarithmic, Negative Binomial, Poisson.
: Generalized Extreme Value, Generalized Logistic,
Generalized Pareto, Phased Bi-Exponential, Phased Bi-Weibull, Wakeby.

.
.
, ,

.

----------------

) [ (-, +)]

(Laplace-Gauss NORMAL DISTRIBUTION)

.
Gauss
. ,
,
( =3) ( =0)
,

.

1 (...)

f ( x) =

* 2

1*( x ) 2
e 2 ,

~(,)

- Probability Density Function

- Cumulative Distribution Function

1
x
, Laplace // (x)=

2

F(x)=

F(x)=z=

t
x
* e 2

dt

>0 (scale parameter/ ),

R (location parameter/ )

< x < +

NORMAL

Probability Density Function

0,32

0,28

0,24

f(x)

0,2

0,16

0,12
0,08

0,04

0
-0,06

-0,04

-0,02

0,02

0,04

x
His togram

Norm al

~ (,2)
[-, +]68.28%
[-2, +2]95.44%
[-3, +3]99.75%

0,06


1) ~(8,9).
P (5 X 10) .
=8 2=9

z=

z=

58
= -1
3

z=

10 8
= 0.66
3

P (5 X 10) = P (1 z 0,66) =
P ( z 0,66) - P ( z 1) = P ( z 0,66) - (1 P ( z 1))

0,7454-(1-0,8413) = 0,8413
(. )

, (-, 0.66)
(-, -1).
(-1, 0.66)

2) ~(3,2) P ( X 1,5) = 0,7291.

2

z=

z=

1,5 3

z=

1,5

P ( X 1,5) = 0,7291. z= 0.61 (.

)
z<0, ( () > 0),
z= -0.61
-0.61=

1,5

=2,46 ( <0

))

 (LOGISTIC DISTRIBUTION)

f ( x) =

ez
,
2
z

* (1 + e )

X~Logistic(,)

F ( x) =

1
,
1 + ez

z =

>0 (scale parameter), R (location parameter) < x < +

:
.
2 .

: , (
), ( )

( <3) (
>3)

 LOGISTIC
Probability Density Function
0,32

0,28

0,24

f(x)

0,2

0,16

0,12
0,08

0,04

0
-0,06

-0,04

-0,02

0,02

0,04

0,06

x
His togram

Logis tic

CAUCHY (CAUCHY DISTRIBUTION)

Cauchy Augustin Cauchy Hendrik Lorentz

, .
Poisson Kernel.
,
, /
Cauchy .

f ( x) = ( * * (1 + (

x 2 1
) )) ,

X~C(,)

F ( x) =

x
+ 0.5

arctan

>0 (scale parameter ) , R (location parameter)

arctan < x < +

CAUCHY

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

x
Histogram

Cauchy

0,02

0,04

0,06

JOHNSON SU (JOHNSON SU DISTRIBUTION)

Norman Lloyd Johnson (1917-2004).

Johnson SB Log-Normal .

,
,
.
, ,
( =3)
( =0). ,
,
.
, Johnson SB, Johnson, SU Log-Normal
.

f ( x) =

* 2 * z 2 + 1

*e

~ Jsu(,,,)

2
2
0.5 * ( + * ln( z + z + 1))

F ( x) = ( + * ln( z + z 2 + 1))

t
x
1 x 2
z =
, Laplace // (x)=
*e
dt

,,, ,>0. x (,+)

, (shape parameter), (scale parameter), (location parameter)

JOHNSON SU

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

x
Histogram

Johnson SU

0,02

0,04

0,06

LAPLACE DOUBLE EXPONENTIAL

(LAPLACE DOUBLE EXPONENTIAL DISTRIBUTION)

Pierre-Simon Laplace. double

exponential ( )

..

Laplace
( ).

f ( x) = * e

* | x |

~ Laplace(,)

F ( x) =

1 * ( x)
*e
2
1 * (x )
1 *e
2

x>

, >0. x (,+)
(scale parameter ) , (location parameter)

 LAPLACE

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

x
Histogram

Laplace

LOG-NORNAL 3-
(LOG-NORNAL DISTRIBUTION 3)

Log-Normal
.
Log-Normal
.
3 (, ) Log-Normal
.
( / , , , )
)

:
Log-Normal

f ( x) =

ln( x )
0.5 *

( x ) * * 2 *

2
,

~ LogN(,,)

ln( x )

F ( x) =

t
1
Laplace // (x)=
* e 2 dt
x

, , >0. x ( ,+)
(scale parameter ), (shape parameter), (location parameter)

: =0, Log-Normal
2- (Log-Normal 2).
Log-Normal 2
=0

 LOG-NORMAL

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

Histogram

Lognormal (3P)

GAMMA 3- (GAMMA 3 DISTRIBUTION)

(waiting time
models). , ,

Gamma .

f ( x) =

(x )

* ( )

(x )

*e

~ (,,)

F ( x) =

( x ) / ( )
( )

x() Gamma// x() = t a 1 * e t dt

0

, , ,>0, R

x ( ,+)

(shape parameter), (scale parameter) , (location parameter)

: =0, Gamma
2- (Gamma 2).
Gamma 2 =0
Gamma Erlang

GAMMA
Probability Density Function
0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

Histogram

Gamma (3P)

0,04

0,06

WEIBULL 3- (WEIBULL 3 DISTRIBUTION)

Waloddi Weibull
(1887-1979), .
(Exponential) Rayleigh
. , (=1)
Rayleigh (=2). Weibull
. <1,
, =1 , >1
. (. )
Weibull
, ,
..

f ( x) =

x
*

*e

~ W(,,)

F ( x) = 1 e

, , ,>0, R

x ( ,+)

(shape parameter), (scale parameter) , (location parameter)

: =0, Weibull
2- (Weibull 2).
Weibull 2 =0

WEIBULL

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

Histogram

Weibull (3P)

FATIGUE LIFE (BirnbaumSaunders) 3-

(FATIGUE LIFE 3 DISTRIBUTION)

. ,

.
Lognormal, Exponential and Weibull.

 , ,
, .

x
f ( x) =

1 x
x

* *

2* a *(x )

~ BS(,,)

1 x
F ( x) = *

x
2

t
1
Laplace // (x)=
* e 2 dt
x

x2
e 2

2 *

, , ,>0, R

x ( ,+)

(shape parameter), (scale parameter) , (location parameter)

: =0,

Fatigue Life

2- (Fatigue Life 2).

Fatigue Life 2
=0

FATIGUE LIFE

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

Histogram

Fatigue Life (3P)

ERLANG 3 (ERLANG 3 DISTRIBUTION)

Erlang Agner Krarup Erlang (1878

1929). Gamma
Exponential . Agner Krarup Erlang

.

 Erlang Gamma

shape parameter Erlang (m)
shape parameter Gamma () .

Erlang Gamma.

m=1 Erlang Exponential .

f ( x) =

m 1

(x )
*e
m
* ( m)

(x )

~ Erlang(m,,)

F ( x) =

( x ) / ( m)
( m)

x() Gamma// x() = t a 1 * e t dt

0

m, , m N * , >0, R

x ( ,+)

m (shape parameter), (scale parameter) , (location parameter)

: =0, Erlang 2 (Erlang 2).

Erlang 2 =0

 ERLANG

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

Histogram

Erlang (3P)

(EXPONENTIAL DISTRIBUTION)

Poisson .
(..
),
,
, ,
..

. ,

.

f ( x) = * exp *( x )

~ Exp(,)

F ( x) = 1 exp * ( x )

, >0, R

x ( ,+)

(scale parameter) , (location parameter)

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

Histogram

Exponential (2P)

0,04

0,06

PEARSON TYPE 6 4-
(PEARSON TYPE 6 4 DISTRIBUTION)

Karl Pearson (1857-1936)

.
,
, ,
, .

. Pearson Type6 5

.
,
Cauchy, , eta, Gamma, X2 F
.

x a1 1
)
b
f ( x) =
x a1 + a 2
))
b * B(a , a ) * (1 + (
1 2
b
(

~ Pearson6(1,2, b,)

F ( x) = I

x
x +b

(a , a2 )
1

 1, 2, b, 1,2,b>0 ,

x +

1,2 (shape parameter) , b (scale parameter), (location parameter)

a 1
a 1
B Beta: B(1,2)= t 1 * (1 t ) 2 dt
1

Iz Beta: Ix=

B x ( a1 , a 2 )
B (a1 , a 2 )

: =0, Pearson
3- (Pearson 3).
Pearson 3 =0

PEARSON TYPE 6

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

Histogram

Pearson 6 (4P)

0,04

0,06

GENERALIZED EXTREME VALUE

(GENERALIZED EXTREME VALUE DISTRIBUTION)

generalized extreme value

(extreme value theory).
Fisher Tippett, (1928)
Gnedenko
(1943) .
Gumbel,
Frchet Weibull .

.
(), , , , .
,
.

1
1
1
k
(1 + k * z ) k * (1 + k * z )

1
f ( x) =
1

*e
( z e

*e

~ GEV(,,k)

k =0

k 0

1
(1 + k * z ) k

F ( x) =

( z e

z=

1+ k

k 0

k =0

, >0

> 0 k 0 < x < +

k =0

k (shape parameter), (scale parameter ) , (location parameter)

GENERALIZED EXTREME VALUE

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

Histogram

Gen. Extreme Value

0,04

0,06

ERROR (ERROR DISTRIBUTION)

/
,
.
Generalized Extreme Value, Weibull, Log-Normal
, ,
, VaR (Value at Risk) .
GARCH,

f ( x) = c

|c *z|
* 1 * e 0

~ Error(,,k)

( )

|c *z| k

0.5 * 1 + 0

1
( )

F ( x) =
1

( )

|c *z| k

0.5 * 1 0

1
( )

x<

 3
( )
c0 = k
( 1 )

1
2

k *c
0

c1 =
2 * ( 1 )

z=

x() Gamma// x() = t a 1 * e t dt

0

< x < + , k (shape parameter), (scale parameter ) , (location parameter)

: k=2 Error k=1

Laplace

ERROR

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

Histogram

Error

0,02

0,04

0,06

F - (F- DISTRIBUTION)

F R.A. Fisher George W. Snedecor.

.

1
*
f ( x) =
x * B( , )
1

(
(

* x)

2
1

1 + 2

~ F(1,2)

* x + )
2

F ( x) = ( 1 , )
z

1
a 1
a 1
B Beta: B(1,2)= t 1 * (1 t ) 2 dt
0

Iz Beta: Ix=

z=

1 * x

1 * x + 2

0 x < + , v1 , v2 N (1,2 )

B x ( a1 , a 2 )
B(a1 , a 2 )

2 - (CHI-SQUARED DISTRIBUTION)
X2
.
, .
X2
Gamma.

f ( x) =

(x )

(x ) 2 1 *e

~ 2(,)

2 2 * ( )
2

F ( x) =

( )
x
( ) 2
2

( )
2
x

x() Gamma// x() = t a 1 * e t dt

0

() Gamma//

() = t a 1 * e t dt
0

// , R , x ( ,+)
(location parameter)

: =0 X2 .

B) ( [,])

(UNIFORM DISTRIBUTION)

.
.
,
(..
17-18 ,
( ) .

(.. )
,
, /.

, Beta

f ( x) =

1
ba

~ U(a,b)

F ( x) =

xa
ba

a<b

a<x<b.

: To
.

UNIFORM

Probability Density Function

0,32

0,28

0,24

f(x)

0,2

0,16

0,12
0,08

0,04

0
-0,06

-0,04

-0,02

0,02

0,04

0,06

x
Histogram

Uniform

1) . 6;
1/6,
.
6 p=1/6

2) . 5;
{1,2,3,4}
(<5)= P(X = 1) + P(X = 2) + P(X = 3) + P(X = 4)
(<5)= 1/6 + 1/6 + 1/6 + 1/6 = 4/6

2) .
) 10
) 7
)
v)

1
2
3
4
5
6

1
2
3
4
5
6
7

2
3
4
5
6
7
8

3
4
5
6
7
8
9

4
5
6
7
8
9
10

5
6
7
8
9
10
11

6
7
8
9
10
11
12

36 (6*6) .
.

) S . 3
=10. 36.
(S=10)= 3/36

) S . 15
< 7. 36.
(S<7)= 15/36
) .
: (=5)=1/6 : (=5)=1/6 (. 1)
()=1/6*1/6=1/36
5
5 .
(, , ..) p=1/36

v)
: (=2)=1/6 : (=3)=1/6 (2,3)= 1/6*1/6

: (=3)=1/6 : (=2)=1/6 (3,2)= 1/6*1/6
()=(2,3)+(3,2)=1/6*1/6+1/6*1/6=1/36+1/36=2/36
.

( DISTRIBUTION)

.
(a-priori) 4
(, Bernoulli ). Beta
Bernoulli .
4

A-Priori . ..
-Posteriori ( )
. .. .

a 1
a 1
1
( x a) 1 * (b x) 2
*
f ( x) =
a + a 1
B(a , a )
1 2
(b a) 1 2

~ eta(1,2, , b)

F ( x) = I (a , a2 )
z

1, 2, , b 1,2>0 <b,

a xb

1,2 (shape parameter)

1
a 1
a 1
B Beta: B(1,2)= t 1 * (1 t ) 2 dt
0

Iz Beta: Ix=

B x ( a1 , a 2 )
B (a1 , a 2 )


1= 2=1 Beta
1<1 2 1 1=1 2>1 Beta
1>1 2 1 2=1 2<1 Beta
1<1 2<1 Beta U (U-shaped).

1=1 2>2 Beta
1=1 2=2 Beta
1=1 1< 2<2 Beta
1>2 2=1 Beta
1=2 2=1 Beta
1< 1<2 2=1 Beta
1>1, 2>1 Beta unimodal ( .

. unimodal-bimodal )

BETA
Probability Density Function
0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

Histogram

Beta

0,02

0,04

0,06

KUMARASWAMY (KUMARASWAMY DISTRIBUTION)

- Ponnambalam
Kumaraswamy. Beta

.
Beta,
.

f ( x) =

a *a * z
1

a a 1
* (1 z 1 ) 2

(b a)

~ Kumaraswamy(1,2, , b)

a a
2

F ( x) = 1 (1 z 1 )

1, 2, , b 1,2>0 <b,

a x b , z=

xa
,
ba

1,2 (shape parameter)

1<1 2 1 1=1 2>1 Kumaraswamy

1>1 2 1 2=1 2<1 Kumaraswamy
1<1 2<1 Kumaraswamy U (U-shaped).

1=1 2>2 Kumaraswamy
1=1 2=2 Kumaraswamy
1=1 1< 2<2 Kumaraswamy
1>2 2=1 Kumaraswamy
1=2 2=1 Kumaraswamy
1< 1<2 2=1 Kumaraswamy
1>1, 2>1 Kumaraswamy unimodal (
)

 KUMARASWAMY

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

Histogram

Kumaraswamy

.
.

(-Johnson SU- LogNormal )

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

x
Histogram

Lognormal (3P)

Normal

Johnson SU

(-Error- Logistic )
Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

x
Histogram

Error

Logistic

Normal

0,04

0,06

(-Gamma- Weibull )

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

x
Histogram

Normal

Weibull (3P)

Gamma (3P)

(-Gen. Extreme Value- Pearson 6 )

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

x
Histogram
Pearson 6 (4P)

Gen. Extreme Value

Normal

0,04

0,06

(-Fatigue Life- Erlang )

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

x
Histogram

Normal

Erlang (3P)

Fatigue Life (3P)

(-Beta- Kumaraswamy )

Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

x
Histogram

Normal

Kumaraswamy

Beta

0,06

(-Laplace- Cauchy )
Probability Density Function

0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
-0,06

-0,04

-0,02

0,02

0,04

0,06

x
Histogram

Cauchy

Laplace

Normal

.
.
Laplace Cauchy,
.
Easy Fit 5.1

.
Kolmogorov-Smirnov, Anderson-Darling Chi-Squared,

.

.
.

Goodness of Fit Summary

Distribution

Kolmogorov
Smirnov

Anderson
Darling

Chi-Squared

Statistic Rank Statistic Rank Statistic Rank

Normal

0,05615

0,23175

1,5421

Beta

0,05627

0,22765

1,5311

Pearson 6 (4P)

0,05665

0,22592

1,5333

Fatigue Life (3P)

0,05684

0,22559

1,5337

Johnson SU

0,05764

0,19995

1,9826

Lognormal (3P)

0,05888

0,22212

2,0897

10

Error

0,05989

0,20537

1,5881

Gen. Extreme Value 0,06144

0,27963

11

1,0682

Gamma (3P)

0,06228

0,22488

1,5591

Logistic

0,06339

10

0,22756

2,2183

11

Weibull (3P)

0,06475

11

0,3477

12

2,5702

12

Kumaraswamy

0,06487

12

0,34846

13

2,5706

13

Erlang (3P)

0,0685

13

0,2426

10

1,5534

Cauchy

0,0892

14

1,2244

15

10,665

14

Laplace

0,10541

15

0,87108

14

14,147

15

KolmogorovSmirnov. (rank)
Beta Pearson 6 (4P).
Anderson-Darling
(rank) Johnson SU
Error Lognormal (3P).
, Chi-Squared,
Gen. Extreme Value Beta
Pearson 6 (4P)

----------------

BERNOULLI (BERNOULLI DISTRIBUTION)

Bernoulli .
(-).
Bernoulli
(-), (-)
.

f ( x ) = 1 p x=0

f ( x) = p x=1

F ( x) = 1 p x=0

F ( x) = 1 x=1

0<p<1

x={0,1}

: E(X)= p
V(X)= p*(1-p)

 (BINOMIAL DISTRIBUTION)

. ( ) p n .
Bernoulli.

: n=1 Bernoulli.
n de
MoivreLaplace np np(1 p)
.
k n
p :

n
f ( x) = * p x * (1 p) n x ,
x

F ( x) = p * (1 p) n i
i=0

~ (n,p)

n!

=
,
x (n x)! x!

0<p<1

0 x n

n , n N
p 1-p , x=0,1,2,.n
(x )

: E(X)=n*p
V(X)=n*p*(1-p)

1.

48% () 52% ().

) .
)
)
v) .

.

0,1,2,3,4,5 (5,0.48)
(5,0.52).

5
) (=5) = * 0.485 * (1 0.48) 5 5 = 0.025
5

5
) (=1) = * 0.521 * (1 0.52) 5 1 = 0.138
1

 5
iii) ( 1) = 1-(=0)= 1- * 0.480 * (1 0.48) 5 0 = 0.962
0

iv) ( 1) = (=0) + (=1) =

5
5
* 0.52 0 * (1 0.52)5 0 + * 0.521 * (1 0.52)5 1 = 0.025+0.138=0.163
1
0
( )

2.

p=28% .
12 .
:
i) 4 .
ii) 2 .
iii) 3 .

.
(n=12, p=28%).

12
i) (=4) = * 0.28 4 * (1 0.28)12 4 = 0.2197
4

ii) ( 2) = (=0) + (=1) + (=2)

12
12
12
0.280 (1 0.28)12 0 + 0.281 (1 0.28)12 1 + 0.28 2 (1 0.28)12 2
0
1
2



= 0.3037

iii) ( 3) = 1- ( 2) = 1- 0.3037= 0.6963 ( )

POISSON (POISSON DISTRIBUTION)

Poisson

. , Simon Denis
Poisson, (17811840).
Poisson
,
.
: p<0.2 n>20

Poisson.
n>50 p<0.1
= n* p. Poisson
.

f ( x) =

x * e

~ Po(np)

x!

i=0

i!

F ( x) = e *

=n*p>0 (n , p )

0 x < +

: E(X)=
V(X)=

.
1)

p=0.05. 50 .
)
) .

. p=0.05<0.2 n=50>20,
Poisson. =n*p=0.05*20 =2.5
2.5 2 * e 2,5
=0.2562
i) p(X=2)=
2!
i) p(X 2)= p(X=0)+ p(X=1)+ p(X=2) =

2.5 0 * e 2.5 2.51 * e 2.5 2.5 2 * e 2.5

+
+
=0.5432
0!
1!
2!

2) 2 4 2

6
i) 4 ;
ii) ;
iii) . 6
;

2 / 4 12 / 24.
2 /6 8 /24
~(1=12|24) ~(2=8|24)

i) P ( X 4) = 1 P ( X 3) =

1 [ P ( X = 3) + P ( X = 2) + P ( X = 1) + P ( X = 0)] =
12 3
12 2
121
12 0
1 [e 12 *
+ e 12 *
+ e 12 *
+ e 12 *
]=
3!
2!
1!
0!
12 3 12 2 121 12 0
1 e 12 * [
+
+
+
]=
3!
2!
1!
0!
1 e 12 * [288 + 144 + 12 + 1] =
1-0.0027=0,9973

83
ii) (=3) = e *
= 0,0286
3!
8

iii) P ( X = 6 < 6) = (=6) * (<6) =

12 6
(e *
) * [ P (Y = 5) + P (Y = 4) + P (Y = 3) + P (Y = 2) + P (Y = 1) + P (Y = 0)]
6!
81 8 8 0
82
8 4 8 8 3
85
12 6
12
8
8
8
8
) * [ e * + e * +e * + e * + e * +e * ] = 0,0048
(e *
0!
1!
2!
3!
4!
5!
6!
12

(GEOMETRIC DISTRIBUTION)

. ( ) p.
.
n
p :

f ( x) = p * (1 p) x

~Ge(p)

F ( x) = 1 (1 p) x + 1

0<p<1

: E(X)=
V(X)=

0 x < +

1
p

1 p
p2

,
n- n-1 ,
p.

1) . 1 5 ;

1. ,
p=1/6 ( ).

p = 1/6. () 1
q = 1-1/6=5/6. ()
1.

 x . ,
5 ( 5 1) x=4
().

p=1/6, q=5/6 x=4

1
6

5
6

P(x)= * ( ) 4 = 0,0803. 1 5 p=0.0803

2) 93%.

20 ;

19 20 .
,
. :
n p
.
,
.

q=0.93
p=1-q =0.07
x=19 ()
(x)= 0.07*0.9319 = 0.0176. 20
0.0176

 (HYPERGEOMETRIC DISTRIBUTION)

. ( ) n
.

:
m ()
-m (). n .
x .

m N m

*
x

n
x
,
f ( x) =
N

n

X ~ h(N,m,n)

m N m
*

x i ni
F ( x) =
N
i=0

n

: E(X)=
V(X)=

n*m
N

n * m * ( N m) * ( N n)
N 2 * ( N 1)

 n , m ,
N , x

max(0, n+m-N)< x <min(n,m) , 0<n N , 0<m N

a!

=
b (a b)!b!

(. ). n=1
Bernoulli. , m
n p 0
1, .

1) 50 . 5

45 . 10 .
4 10 ;

=50
n=10
m=5 ( 5 )
x=4 ( 4 )

5 50 5

*
4 10 4

f (x) =
=
50

10

5 45
*
4 6 ==0.0039
50

10

4 10
0.0039

2) 52 . 8 .

2 8 ;
( 1,2,3.,10 3
: , , . 52 )

=52
n=8
m=4 ( 4 )
x=2 ( 2 )

4 52 4
*

2 8 2

f (x) =
=
52

8

4 48
*
2 6 ==0.0978
52

8

2 8 p=0.0978

(LOGARITHMIC DISTRIBUTION)

x
,
f ( x) =
x * ln(1 )

~log()

x
1
F ( x) =
*
ln(1 ) = 1
0<<1

: E(X)=
V(X)= p *

1 x < +

p
ln(1 p ) * (1 p )

p + ln(1 p )
(1 p ) 2 * ln 2 (1 p )

excel , .
1) Beta

BETADIST
BETAINV
2) Nomral

NORMDIST
NORMINV
3) X2

CHIDIST
CHIINV
4) F

FDIST
FINV
5) Gamma

GAMMADIST

 GAMMAINV
6) T-student ( .

, 50)
DIST
INV
7) BINOMDIST
8) HYPDEOMDIST
9) Poisson POISSON

(J. Fourastie- F. Laslier)

( .- .)
( .)
( .)
1 -
( .)
Wikipedia
Manual Easy Fit 5.1
Manual Excel 2003