Professional Documents
Culture Documents
Continuous Probability Distributions
Continuous Probability Distributions
Distributions
Continuous Random Variables and
Probability Distributions
• Random Variable: Y
• Cumulative Distribution Function (CDF): F(y)=P(Y≤y)
• Probability Density Function (pdf): f(y)=dF(y)/dy
• Rules governing continuous distributions:
f(y) ≥ 0 y
f ( y )dy 1
b
P(a≤Y≤b) = F(b)-F(a) =
a
f ( y )dy
P(Y=a) = 0 a
Expected Values of Continuous RVs
Expected Value : E (Y ) yf ( y )dy (assuming absolute convergenc e)
E g (Y ) g ( y ) f ( y )dy
Variance : V (Y ) E (Y E (Y )) ( y ) 2 f ( y )dy
2 2
y 2 y f ( y )dy y f ( y )dy 2
2 2 2
yf ( y )dy 2 f ( y )dy
E Y 2 ( ) (1) E Y
2 2 2 2
a( ) b(1) a b
V aY b E (aY b) E (aY b)
2
(ay b) (a b) f ( y )dy
2
(ay a ) 2 f ( y )dy a 2 ( y ) 2 f ( y )dy a 2V (Y ) a 2 2
aY b a
Example – Cost/Benefit Analysis of
Sprewell-Bluff Project (I)
• Subjective Analysis of Annual Benefits/Costs of
Project (U.S. Army Corps of Engineers assessments)
• Y = Actual Benefit is Random Variable taken from a
triangular distribution with 3 parameters:
A=Lower Bound (Pessimistic Outcome)
B=Peak (Most Likely Outcome)
C=Upper Bound (Optimistic Outcome)
6 Benefit Variables
3 Cost Variables
Source: B.W. Taylor, R.M. North(1976). “The Measurement of Uncertainty in Public Water Resource
Development,” American Journal of Agricultural Economics, Vol. 58, #4, Pt.1, pp.636-643
Example – Cost/Benefit Analysis of
Sprewell-Bluff Project (II) ($1000s, rounded)
Benefit/Cost Pessimistic (A) Most Likely (B) Optimistic (C)
Flood Control (+) 850 1200 1500
Hydroelec Pwr (+) 5000 6000 6000
Navigation (+) 25 28 30
Recreation (+) 4200 5400 7800
Fish/Wildlife (+) 57 127 173
Area Redvlp (+) 0 830 1192
Capital Cost (-) -193K -180K -162K
Annual Cost (-) -7000 -6600 -6000
Operation/Maint(-) -2192 -2049 -1742
Example – Cost/Benefit Analysis of Sprewell-
Bluff Project (III) (Flood Control, in $100K)
Triangular Distribution with:
k ( y 8.5) 3.5 8.5 y 12.0
lower bound=8.5 f ( y ) k (15.0 y ) / 3.0 12.0 y 15.0
0 elsewhere ( y 8.5, y 15.0)
Peak=12.0
upper bound=15.0 Triangular Distribution (Not Scaled)
0.9
0.7
Probability Density
Area above 12.0 is 0.5((15.0-12.0)k) = 1.50k 0.5
0.4
0.2
0.1
0
8 8.5 9 9.5 10 10.5 11 11.5 12 12.5 13 13.5 14 14.5 15 15.5 16
Flood Control Benefits ($100K)
Example – Cost/Benefit Analysis of
Sprewell-Bluff Project (IV) (Flood Control)
( y 8.5) 11.375 8.5 y 12.0
f ( y ) (15.0 y ) / 9.75 12.0 y 15.0
0 elsewhere
y 8.5 F ( y ) 0
8.5 y 12 F ( y ) (t 8.50) 11.375 dt (1/11.375) t 2 8.5t
y y
2
8.5 8.5
12 y 15 F ( y ) F (12) (15 t ) 9.75 dt .5385 (1/ 9.75) 15t t 2
y y
2
12 12
.5385 15 y y 2 2 15(12) 12 2 2 9.75
0 y 8.5
3.175824 0.747253 y 0.043956 y 2 8.5 y 12
F ( y)
10.538462 1 . 538462 y 0 .051282 y 2
12 y 15
1 y 15
Example – Cost/Benefit Analysis of Sprewell-Bluff Project (VI) (Flood Control)
0.9
0.8
0.7
0.6
F(y)
0.5
0.4
0.3
0.2
0.1
0
8 8.5 9 9.5 10 10.5 11 11.5 12 12.5 13 13.5 14 14.5 15 15.5 16
y
Example – Cost/Benefit Analysis of Sprewell-Bluff Project
(VII) (Flood Control)
12 15
12 y 8.5 15 15 y y3 8.5 y 2 15 y 2 y3
E (Y ) yf ( y )dy y dy 12 y 11.375 dy 29.25 19.5 22.75 34.125
8 .5
9. 75 8.5 12
123 8.5(12) 2 8.53 8.53 153 153 15(12) 2 123
29.25 19 . 5 29.25 19. 5 22. 75 34. 125 22. 75 34. 125
59.08 62.77 21.00 31.49 148.35 98.90 94.95 50.64
3.69 10.49 49.45 44.41 11.84
12 15
2 y 8.5 2 15 y y 4 8.5 y 3 15 y 3 y4
E Y y f ( y )dy y
12 15
2 2
dy y dy
8.5
9. 75 12
11. 375 39 29 .25 8.5 34 .125 45.5 12
12 4 8.5(12) 3 8.54 8.54 154 154 15(12) 3 12 4
39 29. 25 39 29.25 34 . 125 45 .5 34. 125 45. 5
531.69 502.15 133.85 178.46 1483.52 1112.64 759.56 455.74
29.54 44.61 370.88 303.82 141.21
V (Y ) E Y 2 E (Y ) 141.21 11.84 2 141.21 140.19 1.02
2
1.02 1.01
Uniform Distribution
• Used to model random variables that tend to occur
“evenly” over a range of values
• Probability of any interval of values proportional to its
width
• Used to generate (simulate) random variables from
virtually any distribution
• Used as “non-informative prior” in many Bayesian
analyses
1 0 ya
b a a yb
ya
f ( y) F ( y) a yb
b a
0 elsewhere 1 yb
Uniform Distribution - Expectations
2 b
b 1 1 y b 2 a 2 (b a )(b a ) b a
E (Y ) y dy
a
ba ba 2 a
2(b a ) 2(b a ) 2
3 b
b 3 a 3 (b a )( a 2 b 2 ab)
E Y 2
b 1 1 y
y2 dy
a
ba ba 3 a
3(b a ) 3(b a )
(a 2 b 2 ab)
3
2
ab) b a
V (Y ) E Y E (Y )
2 2
2 ( a b
2
3 2
4(a 2 b 2 ab) 3(b 2 a 2 2ab) a 2 b 2 2ab (b a ) 2
12 12 12
(b a ) 2 b a
0.2887(b a )
12 12
Exponential Distribution
• Right-Skewed distribution with maximum at y=0
• Random variable can only take on positive values
• Used to model inter-arrival times/distances for a
Poisson process
1 y /
e y0
f ( y)
0 elsewhere
F ( y)
y 1 t
e dt
1
1
1 t
e
y
e y e 0 1 e y y0
0
0
Exponential Density Functions (pdf)
Exponential pdf's
1.2
0.8
f(y|th=1)
f(y|th=2)
f(y)
0.6
f(y|th=5)
f(y|th=10)
0.4
0.2
0
0 1 2 3 4 5 6 7 8 9 10
y
Exponential Cumulative Distribution Functions (CDF)
Exponential CDF
0.9
0.8
0.7
0.6
F(y|th=1)
F(y|th=2)
F(y)
0.5
F(y|th=5)
F(y|th=10)
0.4
0.3
0.2
0.1
0
0 3 6 9 12 15
y
Gamma Function
( ) y 1e y dy
0
( 1) y e y dy Integratin g by Parts :
0
u y du y 1dy
dv e y dy v e y
y
( 1) y e dy uv vdu y e
y
y 1e y dy
0 0 0
0 (0) y 1e y dy ( ) (Recursive Property)
0
1
(2) 2 (2 1)!
2
EY y e 2 1 y
dy
1 2 y
y e dy
y 31 y
e dy
0
0 0
1
(3) 3 2 (3 1)! 2 2
V (Y ) E Y 2 E (Y ) 2 2 ( ) 2 2
2
Exponential Distribution - MGF
1
M (t ) E e tY ty 1 y
1 y t
e e dy 0 e dy
0
1t
1 y 1 y *
e dy e
dy where *
0 0 1 t
1 1 y * * * 1
M (t ) e ( 0 1) (1 t ) 1
1 * 0 1 t
E (Y ) M ' (0)
V (Y ) M ' ' (0) M ' (0) 2 2 2 2
2
Exponential/Poisson Connection
• Consider a Poisson process with random variable X being
the number of occurences of an event in a fixed time/space
X(t)~Poisson(t)
• Let Y be the distance in time/space between two such
events
• Then if Y > y, no events have occurred in the space of y
1 1 y
( ) y e y 0, , 0
f ( y)
0 otherwise
Obtaining Probabilities in EXCEL:
To obtain: F(y)=P(Y≤y) Use Function: =GAMMADIST(y,,1)
Gamma/Exponential Densities (pdf)
Exponential and Gamma density functions
0.5
0.4
0.3
exp(2.0)
exp(5.0)
f(y)
gam(2,2)
gam(2,3)
gam(3,2)
0.2
0.1
0
0 2 4 6 8 10
y
Gamma Distribution - Expectations
1 1 y 1
E (Y ) y
y e
dy 0
y y
e dy
0
( ) ( )
1 1 ( 1)
0
( 1) 1 y 1
y e dy
( 1)
( ) ( ) ( )
( )
( )
1 y
E Y y
2
2 1
y e
dy
1
0
y 1 y
e dy
0
( ) ( )
1 1 ( 2) 2
0
( 2 ) 1 y 2
y e dy
( 2)
( ) ( ) ( )
( 1)( 1) 2 ( 1)( ) 2
( 1)
( ) ( )
V (Y ) E Y 2 E (Y ) ( 1) ( ) 2 2 2 2 2 2 2
2
Gamma Distribution - MGF
1 y
M (t ) E e 1
tY
e ty
y e dy
0
( )
1 1 t
1 y t
1 y
0 0
1 1
y e dy y e dy
( ) ( )
1
( ) 0
1 y *
y e dy where *
1 t
M (t )
1
( )
( )
*
(1 t )
M ' (t ) (1 t ) 1 ( ) (1 t ) 1
M ' ' (t ) ( 1) (1 t ) 2 ( ) ( 1) 2 (1 t ) 2
E (Y ) M ' (0)
V (Y ) M ' ' (0) M ' (0) ( 1) 2 ( ) 2 2
2
Gamma Distribution – Special Cases
• Exponential Distribution –
Y~
2
Normal (Gaussian) Distribution
• Bell-shaped distribution with tendency for individuals to
clump around the group median/mean
• Used to model many biological phenomena
• Many estimators have approximate normal sampling
distributions (see Central Limit Theorem)
1 ( y )2
1
f ( y) e 2 2
y , , 0
2 2
Normal Densities
0.045
0.04
0.035
0.03
N(100,400)
0.025 N(100,100)
f(y)
N(100,900)
0.02 N(75,400)
N(125,400)
0.015
0.01
0.005
0
0 20 40 60 80 100 120 140 160 180 200
y
Normal Distribution – Normalizing Constant
( y )2
Consider t he integral : e 2 2
dy k (we want to solve for k )
y dz 1
Changing variables : z dy dz
dy
( y )2 z2 z2
k
k e 2 2
dy e 2
dz e 2 dz
z12 z 22
2 z2 z2 1
k 1 2
e dz1 e dz 2 e 2
2 2
dz1dz2
1
2 r2 2 2 2
e 2
d (0 (1)) d d 0
2
0 0 0
r 0
2
k
2 k 2 2 2 k 2 2
Obtaining Value of
From Previous slide, we get : e z2 2
dz 2
1
e z2 2
dz 2
0
2
1 1 2 1 u
Now, Consider : u e du u 1 2 e u du
2 0 0
z2
Changing Variables : u du zdz
2
1 2
1 z
2
1 z2 2
e z2 2
zdz 2 e zdz
2 0 2 0
z
1
2 e z2 2
dz 2 2
0
2
Normal Distribution - Expectations
1 12 z 2
Z ~ N (0,1) f ( z ) e
2
1 1 1
1 z2 1 z2 1 z2
E ( Z ) z e 2 dz
ze 2
dz e
2 0 (0) 0
2 2 2
1 12 z 2 1
1 2 2 z2
2
E Z z 2
e dz 2
z e dz
2 2 0
1
Changing Variables : u z 2 du 2 zdz du zdz
2
1
1 2 2 z2 2 12 z 2 2 u 2 1
2 z e dz ze zdz u e du
2 0
2 0
2 0
2
1
3 2 1 1 3 1 1 1 3/ 2 2
32
u 2
u e du 2 3 2
2 1
2 0
2 2 2 2 2 2 2
V ( Z ) E Z 2 E ( Z ) 1 0 2 1 1
2
Note : If Y ~ N , then Y Z
2
E (Y ) E ( Z ) E ( Z ) (0)
V (Y ) V ( Z ) 2V ( Z ) 2 (1) 2
Normal Distribution - MGF
1 1 y 2 y2 y 2
M (t ) E e e
tY
ty
2 2
exp dy
1
2 2 2 2 2 dy
exp ty
2
2
2 2
1 y2 y ( t 2 ) 2
2
exp 2 2 dy
2 2 2
2
Completing the square : ( t 2 ) 2 2 2 t 2 t 2 2
1 y 2 y ( t 2 ) 2 2 t 2 t 2 2
2t 2 t 2
2
2
M (t ) exp 2 2 dy
2 2 2 2
2 2 2
2
1 y 2
y ( t 2 ) 2 2 t 2 t 2
2
2 t 2 t 2
2
2
exp 2 dy
2 2 2
2 2
2 2
1
exp
1 y ( t 2 ) 2 2 t 2 t 2 2
2
dy
2 2
2 2 2
exp
2 t 2 t 2 2
1
exp
1 y ( t 2 ) 2
dy
2 2
2 2
2 2
The last integral being 1, since it is integratin g over the density of a normal R.V. : Y ~ N t 2 , 2
M (t ) exp
2 t 2 t 2 2
exp t
t 2 2
2 2 2
Normal(0,1) – Distribution of Z2
1
1 z
1 z 2 t
M Z 2 (t ) E etZ e tz
2 2 2
e 2
dz e 2
dz
2 2
1 2 t 2
2 z2 2 z2
2
0
e 2
dz
0
e 1 2 t
dz
1
Changing Variables : u z z u and dz 2
du
2 u
2 1 2
2 u 1 1 1 u
M Z 2 (t )
0
e 1 2 t
2 u
du
2
0
u 2
e 1 2 t
du
12
1 1 2 2
(1 2t ) 1 2 (1 2t ) 1 2
2 2 1 2t 2
Z 2 ~ 12
Beta Distribution
• Used to model probabilities (can be generalized to
any finite, positive range)
• Parameters allow a wide range of shapes to model
empirical data
( ) 1 1
( )( ) y (1 y ) 0 y 1, , 0
f ( y)
0 otherwise
4.5
3.5
Beta(1,1)
2.5 Beta(2,2)
f(y)
Beta(4,1)
2 Beta(1,3)
Beta(5,5)
1.5
0.5
0
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
y
Weibull Distribution
0 y0
F ( y)
y
1 exp y 0 ( , 0)
dF ( y ) y 1 y
y exp
1
f ( y) y exp for y 0
dy
1 y
E (Y ) y y exp dy
0
y y 1
Changing variables : u du dy and y (u )1
y 1
E (Y ) y y exp dy (u )1 e u du 1 u1 e u du 1 1
1
0
0 0
1 y 2
EY
2
y y exp
2
dy (u ) 2 e u du 2 u 2 e u du 2 1
0
0 0
2 1
V (Y ) E Y 2 E (Y ) 2 1 2 1
2
Note: The EXCEL function WEIBULL(y, uses parameterization: *=
Weibull Density Functions (pdf)
Weibull pdf's
1.2
0.8
W(1,1)
W(1,2)
f(y)
0.6
W(2,1)
W(2,2)
0.4
0.2
0
0 1 2 3 4 5 6 7 8 9 10
y
Lognormal Distribution
2
1 log y
1
e 2
y 0, , 0
2y 2 2
f ( y)
0 otherwise
Note : Y * ln( Y ) ~ N , 2
2 12 2 2
E (Y ) E e M Y * (t 1) exp (1)
Y*
e
2
2 2 2 2 2
2
Y* 2
2Y *
E Y E e E e M Y * (t 2) exp (2)
2
e
V (Y ) E Y E (Y ) e 2 2 e 2
2 2
2
1.2
0.8
LN(0,1)
LN(0,4)
f(y)
0.6
LN(1,1)
LN(1,4)
0.4
0.2
0
0 1 2 3 4 5 6 7 8
y