Analytical Profile of Coleus Forskohlii | Forskolin .pptx
Master's Thesis defence presentation
1. Return Interval Distribution of Extreme Events in Long
memory Time Series With Two Scaling Exponents
Smrati Kumar Katiyar
Department of Physics
IISER, Pune
May 3, 2011
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 1 / 27
2. 1 Explanation for the title
2 Statistical test for long memory
3 Foundation stone for our work
4 our work
Analytical approach
Numerical approach to the problem
Comparison of analytical and numerical results
5 Long memory probability process with two scaling exponents
6 conclusion
7 future direction
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 2 / 27
3. What are the key terms?
Return interval distribution of extreme events in long memory time series
with two scaling exponents.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 3 / 27
4. What are the key terms?
Return interval distribution of extreme events in long memory time series
with two scaling exponents.
1 Return interval and extreme events
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 3 / 27
5. What are the key terms?
Return interval distribution of extreme events in long memory time series
with two scaling exponents.
1 Return interval and extreme events
2 Long memory time series
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 3 / 27
6. What are the key terms?
Return interval distribution of extreme events in long memory time series
with two scaling exponents.
1 Return interval and extreme events
2 Long memory time series
3 Scaling exponents
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 3 / 27
7. Return interval and extreme events
Given a time series X(t)
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 4 / 27
8. Return interval and extreme events
Given a time series X(t)
0 20 40 60 80 100
t
-4
-3
-2
-1
0
1
2
3
x(t)
threshold
r1 r2 r3
Figure: Return intervals and extreme events
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 4 / 27
9. Aim of our project work
Example : let say we are given a time series X(t) and there are total 11
time instants at which the value of X is more than the threshold(q).
Those time instants are,
t = 0, 1, 3, 5, 6, 7, 10, 11, 12, 14, 16
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 5 / 27
10. Aim of our project work
Example : let say we are given a time series X(t) and there are total 11
time instants at which the value of X is more than the threshold(q).
Those time instants are,
t = 0, 1, 3, 5, 6, 7, 10, 11, 12, 14, 16
So the return intervals will be :
return intervals = 1, 2, 2, 1, 1, 3, 1, 1, 2, 2
out of these 10 return intervals we have
5 return intervals of length 1
4 return intervals of length 2
and 1 return interval of length 3
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 5 / 27
11. Aim of our project work
Example : let say we are given a time series X(t) and there are total 11
time instants at which the value of X is more than the threshold(q).
Those time instants are,
t = 0, 1, 3, 5, 6, 7, 10, 11, 12, 14, 16
So the return intervals will be :
return intervals = 1, 2, 2, 1, 1, 3, 1, 1, 2, 2
out of these 10 return intervals we have
5 return intervals of length 1
4 return intervals of length 2
and 1 return interval of length 3
so the probability of occurance of return interval of length 1 will be
P(1) = 5
10,
similarly P(2) = 4
10 and P(3) = 1
10
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 5 / 27
12. Long memory time series
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 6 / 27
13. Long memory time series
Plot of sample autocorrelation function (ACF) ρk against lag k is one of
the most useful tool to analyse a given time series.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 6 / 27
14. Long memory time series
Plot of sample autocorrelation function (ACF) ρk against lag k is one of
the most useful tool to analyse a given time series.
ρk =
n
t=k+1(xt −x)(xt−k −x)
n
t=1(xt −x)2
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 6 / 27
15. Long memory time series
Plot of sample autocorrelation function (ACF) ρk against lag k is one of
the most useful tool to analyse a given time series.
ρk =
n
t=k+1(xt −x)(xt−k −x)
n
t=1(xt −x)2
For long memory processes
ρk → Cρk−γ
as k → ∞
where Cρ > 0 and γ ∈ (0, 1)
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 6 / 27
16. Long memory time series
Plot of sample autocorrelation function (ACF) ρk against lag k is one of
the most useful tool to analyse a given time series.
ρk =
n
t=k+1(xt −x)(xt−k −x)
n
t=1(xt −x)2
For long memory processes
ρk → Cρk−γ
as k → ∞
where Cρ > 0 and γ ∈ (0, 1)
0 10 20 30 40 50 60
0.00.20.40.60.81.0
Lag
ACF
Series a
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 6 / 27
17. Long memory time series
Plot of sample autocorrelation function (ACF) ρk against lag k is one of
the most useful tool to analyse a given time series.
ρk =
n
t=k+1(xt −x)(xt−k −x)
n
t=1(xt −x)2
For long memory processes
ρk → Cρk−γ
as k → ∞
where Cρ > 0 and γ ∈ (0, 1)
0 10 20 30 40 50 60
0.00.20.40.60.81.0
Lag
ACF
Series a
A Long memory process is trend reinforcing, which means the direction
(up or down compared to the last value) of the next value is more likely
the same as current value.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 6 / 27
19. Scaling exponents
The most common power laws relate two variables and have the form
f (x) ∝ xα
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 7 / 27
20. Scaling exponents
The most common power laws relate two variables and have the form
f (x) ∝ xα
Here α is called the scaling exponent. where the word ”scaling” denotes
the fact that a power-law function satisfies
f (cx) = cαf (x) ∝ f (x)
Here c is a constant.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 7 / 27
21. Statistical test for long memory
How to find whether a given time series x(t) has long memory or not?
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 8 / 27
22. Statistical test for long memory
How to find whether a given time series x(t) has long memory or not?
Detrended fluctuation analysis
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 8 / 27
23. Statistical test for long memory
How to find whether a given time series x(t) has long memory or not?
Detrended fluctuation analysis
x(t) is the time series. (t = 1, 2, 3, .......Nmax )
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 8 / 27
24. Statistical test for long memory
How to find whether a given time series x(t) has long memory or not?
Detrended fluctuation analysis
x(t) is the time series. (t = 1, 2, 3, .......Nmax )
y(k) = k
i=1(xi − x ) cumulative sum or profile
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 8 / 27
25. Statistical test for long memory
How to find whether a given time series x(t) has long memory or not?
Detrended fluctuation analysis
x(t) is the time series. (t = 1, 2, 3, .......Nmax )
y(k) = k
i=1(xi − x ) cumulative sum or profile
Divide y(k) into time window of length n samples. In each box of length
n, we fit y(k), using a polynomial function of order l, which represents the
trend in that box. The y coordinate of the fit line in each box is denoted
by yn(k). Since we use a polynomial fit of order l, we denote the algorithm
as DFA-l.
0 100 200 300 400 500 600 700 800 900 1000
0
50
100
150
200
250
300
350
K
Yk
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 8 / 27
26. The integrated signal y(k) is detrended by subtracting the local trend
yn(k) in each box of length n.
For a given box size n, the root-mean-square (rms) fluctuation for this
integrated and detrended signal is calculated:
F(n) = 1
Nmax
Nmax
k=1 [y(k) − yn(k)]2
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 9 / 27
27. The integrated signal y(k) is detrended by subtracting the local trend
yn(k) in each box of length n.
For a given box size n, the root-mean-square (rms) fluctuation for this
integrated and detrended signal is calculated:
F(n) = 1
Nmax
Nmax
k=1 [y(k) − yn(k)]2
The above computation is repeated for a broad range of scales (box size
n) to provide a relationship between F(n) and the box size n.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 9 / 27
28. The integrated signal y(k) is detrended by subtracting the local trend
yn(k) in each box of length n.
For a given box size n, the root-mean-square (rms) fluctuation for this
integrated and detrended signal is calculated:
F(n) = 1
Nmax
Nmax
k=1 [y(k) − yn(k)]2
The above computation is repeated for a broad range of scales (box size
n) to provide a relationship between F(n) and the box size n.
A power-law relation between the average root-meansquare fluctuation
function F(n) and the box size n indicates the presence of scaling
F(n) ∝ nα
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 9 / 27
29. We can fit the log-log plot with a straight line and the slope of that line
will be the scaling exponent.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 10 / 27
30. We can fit the log-log plot with a straight line and the slope of that line
will be the scaling exponent.
0 0.2 0.4 0.6 0.8 1
ln n
0
0.2
0.4
0.6
0.8
1
lnF(n)
Figure: log-log plot of F(n) Vs n
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 10 / 27
31. We can fit the log-log plot with a straight line and the slope of that line
will be the scaling exponent.
0 0.2 0.4 0.6 0.8 1
ln n
0
0.2
0.4
0.6
0.8
1
lnF(n)
Figure: log-log plot of F(n) Vs n
When slope of line is in range (1/2,1) ,The time series displays long
memory.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 10 / 27
32. Foundation stone for our work
for a long memory time series with one scaling exponent, the probability
distribution of return intervals are known (Santhanam et. al, 2008)
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 11 / 27
33. Foundation stone for our work
for a long memory time series with one scaling exponent, the probability
distribution of return intervals are known (Santhanam et. al, 2008)
P(R) = a R−(1−γ) e
−( a
γ
)Rγ
Here R is the scaled return interval
R = r
r ,where r are the actual return intervals r = 1, 2, 3, 4, ......
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 11 / 27
34. our work
What about time series with two scaling exponent?
How to calculate their return interval distributions?
Examples of these kind of time series are:
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 12 / 27
35. our work
What about time series with two scaling exponent?
How to calculate their return interval distributions?
Examples of these kind of time series are:
high frequency financial data,
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 12 / 27
36. our work
What about time series with two scaling exponent?
How to calculate their return interval distributions?
Examples of these kind of time series are:
high frequency financial data,
network traffic of a web server etc.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 12 / 27
37. our work
What about time series with two scaling exponent?
How to calculate their return interval distributions?
Examples of these kind of time series are:
high frequency financial data,
network traffic of a web server etc.
0 0.2 0.4 0.6 0.8 1
ln n
0
0.2
0.4
0.6
0.8
1
lnF(n)
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 12 / 27
38. our work
What about time series with two scaling exponent?
How to calculate their return interval distributions?
Examples of these kind of time series are:
high frequency financial data,
network traffic of a web server etc.
0 0.2 0.4 0.6 0.8 1
ln n
0
0.2
0.4
0.6
0.8
1
lnF(n)
Figure: Podobnik et al. PHYSICA A,
2002
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 12 / 27
39. our approach to solve the problem
analytical approach
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 13 / 27
40. our approach to solve the problem
analytical approach We will consider a probability model for a stationary
process with long memory, given an extreme event at time t = 0, the
probability to find an extreme event at time t = r is given by
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 13 / 27
41. our approach to solve the problem
analytical approach We will consider a probability model for a stationary
process with long memory, given an extreme event at time t = 0, the
probability to find an extreme event at time t = r is given by
Pex (r) =
a1r−(2α1−1) = a1r−(1−γ1) for 0 < r < nx
a2r−(2α2−1) = a2r−(1−γ2) for nx < r < ∞
where 0.5 < α1, α2 < 1 are DFA exponents and 0 < γ1, γ2 < 1 are
autocorrelation exponents
nx is the crossover scale
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 13 / 27
42. After a very long algebra we find the return interval distribution
P(r) =
a1r−(1−γ1)e−(a1/γ1)rγ1
for 0 < r < nx
Ca2r−(1−γ2)e−(a2/γ2)rγ2
for nx < r < ∞
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 14 / 27
43. After a very long algebra we find the return interval distribution
P(r) =
a1r−(1−γ1)e−(a1/γ1)rγ1
for 0 < r < nx
Ca2r−(1−γ2)e−(a2/γ2)rγ2
for nx < r < ∞
How to find three unknowns a1, a2 and C ?
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 14 / 27
44. After a very long algebra we find the return interval distribution
P(r) =
a1r−(1−γ1)e−(a1/γ1)rγ1
for 0 < r < nx
Ca2r−(1−γ2)e−(a2/γ2)rγ2
for nx < r < ∞
How to find three unknowns a1, a2 and C ? we need three equations........
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 14 / 27
45. After a very long algebra we find the return interval distribution
P(r) =
a1r−(1−γ1)e−(a1/γ1)rγ1
for 0 < r < nx
Ca2r−(1−γ2)e−(a2/γ2)rγ2
for nx < r < ∞
How to find three unknowns a1, a2 and C ? we need three equations........
normalization equation
∞
0
P(r)dr = 1.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 14 / 27
46. After a very long algebra we find the return interval distribution
P(r) =
a1r−(1−γ1)e−(a1/γ1)rγ1
for 0 < r < nx
Ca2r−(1−γ2)e−(a2/γ2)rγ2
for nx < r < ∞
How to find three unknowns a1, a2 and C ? we need three equations........
normalization equation
∞
0
P(r)dr = 1.
normalizing r to unity
∞
0
rP(r)dr = 1
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 14 / 27
47. After a very long algebra we find the return interval distribution
P(r) =
a1r−(1−γ1)e−(a1/γ1)rγ1
for 0 < r < nx
Ca2r−(1−γ2)e−(a2/γ2)rγ2
for nx < r < ∞
How to find three unknowns a1, a2 and C ? we need three equations........
normalization equation
∞
0
P(r)dr = 1.
normalizing r to unity
∞
0
rP(r)dr = 1
using continuity condition
a1r−(1−γ1) = a2r−(1−γ2) at r = nx
a1n
−(1−γ1)
x = a2n
−(1−γ2)
x
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 14 / 27
48. final equations for a1, a2 and C
a1n
−(1−γ1)
x = a2n
−(1−γ2)
x
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 15 / 27
49. final equations for a1, a2 and C
a1n
−(1−γ1)
x = a2n
−(1−γ2)
x
Ce−(a2/γ2)n
γ2
x = e−(a1/γ1)n
γ1
x
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 15 / 27
50. final equations for a1, a2 and C
a1n
−(1−γ1)
x = a2n
−(1−γ2)
x
Ce−(a2/γ2)n
γ2
x = e−(a1/γ1)n
γ1
x
C(γ2/a2)1/γ2
nx Eγ2−1
γ2
(n
γ2
x )
γ2
− (γ1/a1)1/γ1
nx Eγ1−1
γ1
(n
γ1
x )
γ1
= 1
Here En(x) =
∞
1
e−xt
tn dt =
1
0 e−x/ηη(n−2)dη
En(x) is known as exponential integral function.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 15 / 27
51. numerical approach to the problem
first and only challenge with this approach : to get a long memory time
series which contains two different scaling exponents.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 16 / 27
52. numerical approach to the problem
first and only challenge with this approach : to get a long memory time
series which contains two different scaling exponents.
The model
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 16 / 27
53. numerical approach to the problem
first and only challenge with this approach : to get a long memory time
series which contains two different scaling exponents.
The model
Step 1:
set the length of time series, say, l = 105.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 16 / 27
54. numerical approach to the problem
first and only challenge with this approach : to get a long memory time
series which contains two different scaling exponents.
The model
Step 1:
set the length of time series, say, l = 105.
Step 2:
generate a series of random numbers yi i = 0......(l − 1) which follow
gaussian distribution with mean 0 and variance 1
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 16 / 27
55. numerical approach to the problem
first and only challenge with this approach : to get a long memory time
series which contains two different scaling exponents.
The model
Step 1:
set the length of time series, say, l = 105.
Step 2:
generate a series of random numbers yi i = 0......(l − 1) which follow
gaussian distribution with mean 0 and variance 1
Step 3:
generate a series of coefficients defined as:
Cα
i =
Γ(i − α)
Γ(−α)Γ(i + 1)
= −
α
Γ(1 − α)
Γ(i − α)
Γ(i + 1)
α =
α1 for 0 < i < nx
α2 for nx < i < ∞
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 16 / 27
56. Both α1 and α2 belong to the interval (−0.5, 0)
The asymptotic behaviour of Cα
i for large i can be written as
Cα
i ≃ −
α
Γ(1 − α)
i−(1+α)
for i ≫ 1
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 17 / 27
57. Both α1 and α2 belong to the interval (−0.5, 0)
The asymptotic behaviour of Cα
i for large i can be written as
Cα
i ≃ −
α
Γ(1 − α)
i−(1+α)
for i ≫ 1
Step 4:
Now, get a series yα
i using yi and Cα
i according to the relation
yα
i =
i
j=0
yi−jCα
j i = 0.....(l − 1) (1)
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 17 / 27
58. DFA of time series generated using previous model
0 1 2 3 4 5 6
log (n)
0
1
2
3
4
logF(n)
DFA analysis of time series
crossover region
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 18 / 27
59. comparison of analytical and numerical results
try to fit P(r) = ar−(1−γ)e−(c/γ)rγ
to each segment, according to their
corresponding γ values
-5 -4 -3 -2 -1 0 1 2
ln (R)
-8
-7
-6
-5
-4
-3
lnP(R)
segment 1
segment2
break point
discrepancy because of threshold dependence of constants and long
memory in return intervals.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 19 / 27
61. Long memory probability process with two scaling
exponents
To remove discrepancy because of long memory in return intervals. We
will generate return intervals such that they have no dependence on each
other.
first determine the constants a1 and a2 by normalizing it in the region
kmin = 1 and kmax .
kmax
1
Pex (r)dr =
nx
1
a1r−(1−γ1)
dr +
kmax
nx
a2r−(1−γ2)
dr = 1
Use continuity condition as well and solve for a1 and a2.
a1 =
1
[n
γ1
x
γ1
− 1
γ1
+ k
γ2
max n
γ1−γ2
x
γ2
− n
γ1
x
γ2
]
a2 =
1
[n
γ2
x
γ1
− n
γ2−γ1
x
γ1
+ k
γ2
max
γ2
− n
γ2
x
γ2
]
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 21 / 27
62. Now generate a random number ξr from a uniform distribution at every r
and compare it with the value of Pex (r). A random number is accepted as
an extreme event if ξr < Pex (r) at any given value of r. If ξr ≥ Pex (r),
then it is not an extreme event. Using this procedure we can generate a
series of extreme events.
-6 -4 -2 0 2
ln (R)
-9
-8
-7
-6
-5
-4
-3
-2
lnP(R)
segment 2
segm
ent 1
break point
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 22 / 27
63. -6.5
-6
-5.5
-5
-4.5
-4
-3.5
-3
-2.5
-2
-5.5 -5 -4.5 -4 -3.5 -3 -2.5 -2 -1.5
lnP(R)
ln(R)
return interval distribution of segment 1
-8.5
-8
-7.5
-7
-6.5
-6
-1 -0.5 0 0.5 1 1.5 2
lnP(R)
ln(R)
return interval distribution of segment 2
P(r) =
a1r−(1−γ1)e−(a1/γ1)rγ1
for 0 < r < nx
Ca2r−(1−γ2)e−(a2/γ2)rγ2
for nx < r < ∞
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 23 / 27
64. In the previous slide, for segment(1) in place of a1, we have two variables a
and b. Why we have two different variables? the possible reason is that
for normalization integrals we have lower limit as 0 but in reality the
minimum size of return interval is 1. So even after scaling, the minimum
value of lower limit is 1/ r .
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 24 / 27
65. conclusion
for a long memory time series with two different scaling exponent
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 25 / 27
66. conclusion
for a long memory time series with two different scaling exponent
There is a break point in the return interval distribution graph.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 25 / 27
67. conclusion
for a long memory time series with two different scaling exponent
There is a break point in the return interval distribution graph.
For each scaling exponent there will be a different segment in return
interval distribution.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 25 / 27
68. conclusion
for a long memory time series with two different scaling exponent
There is a break point in the return interval distribution graph.
For each scaling exponent there will be a different segment in return
interval distribution.
Each segment still follow a distribution of the form which is product of
power law and stretched exponential.
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 25 / 27
70. future direction
the model that we have used to generate time series with more than one
scaling exponent need a fine tuning so that we can test our analytical
results more accurately
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 26 / 27
71. future direction
the model that we have used to generate time series with more than one
scaling exponent need a fine tuning so that we can test our analytical
results more accurately
we should also think of the effects of long memory in return intervals
Katiyar S K (IISER Pune) Thesis Presentation May 3, 2011 26 / 27