Kuliah 8 Hidrologi_2017

Analisis Frekuensi
 FREQUENCY ANALYSIS
• Basic Problem:
To relate the magnitude of extreme events to
their frequency of occurrence through the use
of probability distributions.
 FREQUENCY ANALYSIS
• Practical Problems:
(a) Selection of reasonable & simple distribution.
(b) Estimation of parameters in distribution.
(c) Assessment of risk with reasonable accuracy.
 REVIEW OF BASIC CONCEPTS
Probabilistic
Outcome of a hydrologic event (e.g., rainfall amount & duration; flood
peak discharge; wave height, etc.) is random and cannot be predicted with
certainty.

Terminologies
- Population
The collection of all possible outcomes relevant to the process of
interest. Example:
(1) Max. 2-hr rainfall depth: all non-negative real numbers;
(2) No. of storm in June: all non-negative integer numbers.

- Sample
A measured segment (or subset) of the population.
 REVIEW OF BASIC CONCEPTS
Terminologies
- Random Variable
A variable describable by a probability distribution which
specifies the chance that the variable will assume a particular
value.
Convention: Capital letter for random variables (say, X)
whereas the lower case letter (say, x) for numerical realization
that the random variable X will take.
Example:
X = rainfall amount in 2 hours (a random variable) ;
x = 100.2 mm/2hr (realization).
- Random variables can be
- discrete (eg., no. of rainy days in June) or
- continuous (eg., max. 2-hr rainfall amount, flood discharge)..
 REVIEW OF BASIC CONCEPTS
Terminologies
Frequency & Relative Frequency
o For discrete random variables:
o Frequency is the number of occurrences of a specific event. Relative frequency
is resulting from dividing frequency by the total number of events. e.g.
n = no. of years having exactly 50 rainy days; N = total no. of years.
Let n=10 years and N=100 years. Then, the frequency of having
exactly 50 rainy days is 10 and the relative frequency of having
exactly 50 rainy days in 100 years is n/N = 0.1.
o For continuous random variables:
o Frequency needs to be defined for a class interval.
o A plot of frequency or relative frequency versus class intervals is called
histogram or probability polygon.
o As the number of sample gets infinitely large and class interval length
approaches to zero, the histogram will become a smooth curve, called
probability density function.
 REVIEW OF BASIC CONCEPTS
Terminologies
Probability Density Function (PDF) –

• For a continuous random variable, the PDF must satisfy




-
f ( x) dx  1

and f(x) ≥ 0 for all values of x.

• For a discrete random variable, the PDF must satisfy

 p ( x)  1
all x

and 1≥ p(x) ≥ 0 for all values of x.

REVIEW OF BASIC CONCEPTS
Terminologies
- Cumulative Distribution Function -

For a continuous random variable,

xo
Pr( X  xo )  
-
f ( x) dx

For a discrete random variable, by

Pr( X  x o) = 
all xi  xo
p( xi )
 Statistical Properties of Random Variables
• Population - Synonymous to sample space, which describes
the complete assemblage of all the values representative of a
particular random process.
• Sample - Any subset of the population.
• Parameters - Quantities that are descriptive of the population
in a statistical model. Normally, Greek letters are used to
denote statistical parameters.
• Sample statistics (or simply statistics): Quantities calculated on
the basis of sample observations.
 Mean, Mode, Median, and Quantiles
• Expectation (1st-order moment) measures central tendency of random variable X
  
E  X  = μx =  x f  x  dx =  x dF  x  =  1 - F  x  dx
x x x
- - -
– Mean (m) = Expectation = l1 = location of the centroid of PDF or PMF.
– Two operational properties of the expectation are useful:
•  K  K
E   ak X k  =  a k m k

k=1 
k=1

in which mk=E[Xk] for k = 1,2, …, K.

• For independent random variables,  K  K
E   X k  =  mk
 k=1  k=1
• Mode (xmo) - the value of a RV at which its PDF is peaked. The mode, xmo, can be obtained by
solving  f  x  
x
  =0
 x  x  xmo
• Median (xmd) - value that splits the distribution into two equal halves, i.e,
xmd

Fx  xmd  =  f  x  dx = 0.5
x
-

• Quantiles - 100pth quantile of a RV X is a quantity xp that satisfies P(X  xp) = Fx(xp) = p

• A PDF could be uni-modal, bimodal, or multi-modal. Generally, the mean, median, and mode
of a random variable are different, unless the PDF is symmetric and uni-modal.
Uni-modal and bi-modal distributions

fx(x)

(a) Uni-modal distribution

fx(x)

(b) Bi-modal distribution

 Variance, Standard Deviation, and Coefficient
of Variation
• Variance is the second-order central moment measuring the spreading of a
RV over its range,

Var  X  = m2  s = E  X - μx   =   x - μx  f x  x  dx
2 2 2
x
 
-
• Standard deviation (sx) is the positive square root of the variance.
• Coefficient of variation, Wx=sx/mx, is a dimensionless measure; useful for
comparing the degree of uncertainty of two RVs with different units.
• Three important properties of the variance are:
– (1) Var[c] = 0 when c is a constant.
– (2) Var[X] = E[X2] - E2[X]
– For multiple independent random variables,
 K  K 2 2
Var  ak X k  =  ak s k
 k=1  k=1
where ak =a constant and sk = standard deviation of Xk, k=1,2, ..., K.
 Skewness Coefficient
• Measures asymmetry of the PDF of a random variable
• Skewness coefficient, gx, defined as
μ 3 E   X - μx  
 3

g x = 1.5 =
μ2 s x3
• The sign of the skewness coefficient indicates the degree of
symmetry of the probability distribution function.
• Pearson skewness coefficient –

μ x - x mo
g1 =
• In practice, product-moments
sx higher than 3rd-order are less
used because they are unreliable and inaccurate when
estimated from a small number of samples
• See Table for equations to compute the sample product-
moments.
Relative locations of mean, median, and mode for
positively-skewed, symmetric, and negatively-skewed
distributions.
fx(x)
fx(x)
(a) Positively Skewed, gx>0
(b) Symmetric, gx=0

x x
xmo xmd mx mxxmo=xmd

fx(x)

(c) Negatively skewed, gx<0

x
mx xmd xmo
 Kurtosis (kx)
• Measure of the peakedness of a distribution.
• Related to the 4th central product-moment as
E  X - μx 4 
μ4
kx = 2 =  
μ2 s x4
• For a normal RV, its kurtosis is equal to 3. Sometimes,
coefficient of excess, ex=kx-3, is used.
• All feasible distribution functions, skewness coefficient and
kurtosis must satisfy
g x2  1  k x
 Some Commonly Used Distributions
• NORMAL DISTRIBUTION
 1 2


f N x | mx, s 2
x = 1
exp -
 2
 x - μx

 σ



 , for - < x < 

2π s x   x  

Standardized Variable:
X -m
Z
s

Z has mean 0 and standard deviation 1.

 Some Commonly Used Distributions

• STANDARD NORMAL DISTRIBUTION:

0.5

0.4

(z ) 0.3

0.2

0.1

-3 -2 -1 0 1 2 3

z
 Some Commonly Used Distributions
• LOG-NORMAL DISTRIBUTION
 1  ln( x) - m  2 
f LN  x | m ln x , s ln2 x  =
1
exp -  ln x
 ,x>0
2 s ln x x  2  s ln x  
1.6

(a) mx = 1.0
1.4
1.2 Wx=0.
1.0 3

fLN(x) 0.8
0.6 Wx=0.
0.4 6 Wx=1.3
0.2
0.0
0 1 2 3 4 5 6
x 0.7
0.6 mx =1.65
(b) Wx = 1.30
0.5
0.4
fLN(x) mx =2.25
0.3
0.2 mx =4.50
0.1
0
0 1 2 3 4 5 6
x
 Some Commonly Used Distributions
• Gumbel (Extreme-Value Type I) Distribution
   x - 
 1   x -     
  x -
F EV 1  x |  ,   = exp  - exp  -   for maxima
 f EV 1  x |  ,   = exp -   - exp - 
   for maxima
    
        
  
   x - ξ    1   x -     x -    
= 1 - exp - exp +     for minima = exp +   - exp +     for minima
   β              

fEV1(y)
0.4
Max
Min
0.3

0.2

0.1

0
-4 -3 -2 -1 0 1 2 3 4

y
 Some Commonly Used Distributions
• Log-Pearson Type 3 Distribution
α -1
 x-ξ 
f P 3 x |  ,  ,   =
1 -  x -  / 
  e
β Γ    β 
0.30

4,1
0.25
1,4
0.20

fG(x) 0.15

2,4
0.10

0.05

0.00
0 2 4 6 8 10 12 14

x
 Some Commonly Used Distributions
• Log-Pearson Type 3 Distribution
 ln x  - ξ 
α -1

f LP 3  x |  ,  ,   =
1 - ln( x ) -  / 
  e
x β Γ    β 
with >0, xe when >0 and with >0, xe when <0
 Exercise
• Diketahui Curah Hujan Harian Maksimum sbb
Tahun Sta Margasari Sta Dukuh Waringin Sta Kalibakung
1 147 150 140
2 105 124 110
3 84 109 202
4 91 92 100
5 87 253 125
6 93 215 125
7 112 155 155
8 130 163 101
9 116 177 107
10 97 157 100
11 106 57 127
12 95 98 106
13 130 59 129
14 84 59 125
• 1. Tentukan CH15Wilayah dengan
172 metode Aritmatik
147 180
• 2. Tentukan CH Rata2, Standar Deviasi, Koef Skewness dan Koef Kurtosis, Koef Variasi