Advanced
PARAMETER ESTIMATION AND SPECTRUM OF FRACTIONAL ARIMA PROCESS†
PARAMETER ESTIMATION AND SPECTRUM OF FRACTIONAL ARIMA PROCESS†
Journal of Applied Mathematics & Informatics. 2015. Jan, 33(1_2): 203-210
Copyright © 2015, Korean Society of Computational and Applied Mathematics
  • Received : September 15, 2014
  • Accepted : November 27, 2014
  • Published : January 30, 2015
Download
PDF
e-PUB
PubReader
PPT
Export by style
Share
Article
Author
Metrics
Cited by
TagCloud
About the Authors
JOO-MOK KIM
YUN-KYONG KIM

Abstract
We consider fractional Brownian motion and FARIMA process with Gaussian innovations and show that the suitably scaled distributions of the FARIMA processes converge to fractional Brownian motion in the sense of finite dimensional distributions. We figure out ACF function and estimate the self-similarity parameter H of FARIMA(0, d , 0) by using R/S method. Finally, we display power spectrum density of FARIMA process. AMS Mathematics Subject Classification : Primary 60G10, 60G18. Secondary 60G51.
Keywords
1. Introduction
Traffic measurements in many network environments demonstrate long range dependent process(LRD) and self-similar processes which appear in many contexts, for example, in the analysis of traffic load in high speed networks [3 , 14] . On the other hand, Self-similarity, long range dependence and heavy tailed process have been observed in many time series, i.e. signal processing and finance [5 , 9] .
The models based on self-similarity could reflect the features of LRD only by Hurst parameter [6 , 13] . Because the traditional short range dependent process(SRD) could not reflect self-similar traffic’s attention to the network, FARIMA model and superposition model in which the sojourn time complies with heavy-tailed distributed ON/OFF sources are required [10] .
In particular, A fractional autoregressive integrated moving average process(FARIMA) is widely used in video and network traffic modeling [1 , 2 , 4 , 7] . In this paper, we use the fractionally integrated autoregressive moving average processes with Gaussian innovations to describe convergence to Fractional Brownian motion [8 , 11] .
On the other hand, various methods for estimating the self-similarity parameter H or the intensity of long-range dependence in a time series has investigated [12 , 13] . In particular, we use R/S method for parameter estimation of selfsimilarity in FARIMA processes.
In section 2, we define long range dependence, self-similar process, fractional Brownian motion, fractional Gaussian noise and FARIMA processes with Gaussian innovations. In section 3, we prove the weak convergence of FARIMA processes to fractional Bronian motion. In section 4, we figure out the self-similarity H of FARIMA(0, d , 0) and display the power spectrum density function of fractional autoregressive integrated moving average processes.
2. Definition and Preliminary
In this section we first define short range dependence and long range dependence. Let τX ( k ) be the covariance of stationary stochastic process X ( t ).
Definition 2.1. A stationary stochastic process X ( t ) exhibits short range dependence if
PPT Slide
Lager Image
Definition 2.2. A stationary stochastic process X ( t ) exhibits long range dependence if
PPT Slide
Lager Image
A standard example of a long range dependent process is fractional Brownian motion, with Hurst parameter
PPT Slide
Lager Image
Definition 2.3. A continuous process X ( t ) is self-similar with self-similarity parameter H ≥ 0 if it satisfies the condition:
PPT Slide
Lager Image
where the equality is in the sense of finite-dimensional distributions.
Self-similar processes are invariant in distribution under scaling of time and space. Brownian motion is a Gaussian process with mean zero and autocovariance function
PPT Slide
Lager Image
It is H self-similar with H = 1/2. And, Fractional Brownian motion is important example of self-similar process.
Definition 2.4. A stochastic process { BH ( t )} is said to be a fractional Brownian motion( FBM ) with Hurst parameter H if
  • 1.BH(t) has stationary increments
  • 3.BH(0) = 0a.s.
  • 4. The increments ofBH(t),Z(j) =BH(j+ 1) −BH(j) satisfy
PPT Slide
Lager Image
Definition 2.5. Let
PPT Slide
Lager Image
The sequence { Gj , j Z } is called fractional Gaussian noise (FGN).
Since fractional Brownian motion { BH ( t ) : t R } has stationary increments, its increments Gj form a stationary sequence. Fractional Gaussian noise is a mean zero and stationary Gaussian time series whose autocovariance function τ ( h ) = EGiGi + h is given by
PPT Slide
Lager Image
h ≥ 0. As h → ∞
PPT Slide
Lager Image
Since τ ( h ) = 0 for h ≥ 1 when H = 1/2. the Gi are white noise. When 1/2 < H < 1, they display long-range dependence.
We introduce a FARIMA( p, d, q ) which is both long range dependent and has heavy tails. FARIMA( p, d, q ) processes are capable of modeling both short and long range dependence in traffic models since the effect of d on distant samples decays hyperbolically while the effects of p and q decay exponentially.
Definition 2.6. A stationary process Xt is called a FARIMA ( p, d, q ) process if
PPT Slide
Lager Image
where ϕ ( B ) = 1 − ϕ 1 B − · · · − ϕpBp , θ ( B ) = 1 − θ 1 B − · · · − θqBq and the coefficients ϕ 1 , · · ·, ϕp and θ 1 , · · ·, θq are constants,
PPT Slide
Lager Image
and B is the backward shift operator defined as BiXt = X t i and
PPT Slide
Lager Image
For large lags d , the autocovariance function satisfies for 0 < d < 1/2,
PPT Slide
Lager Image
where Cd = π −1 Γ(1 − 2 d ) sin( πd ). Thus, for large lags d , the autocovariance function has the same power decay as the autocovariance of fractional Gaussian noise. Relating the exponents gives
PPT Slide
Lager Image
3. Weak Convergence of FARIMA to Fractional Brownian motion
Lemma 3.1. Fix 1/2 < H < 1 and let { Zj, j = · · ·, −1, 0, 1, · · · } be a stationary Gaussian sequence with mean zero and autocovariance function τ ( j ) = EZ 0 Zj satisfying:
PPT Slide
Lager Image
Then the finite dimensional distributions of
PPT Slide
Lager Image
converge to those of { σ 0 BH ( t ), 0 ≤ t ≤ 1} where
PPT Slide
Lager Image
Proof . Theorem 7.2.11 of [6] . □
Theorem 3.2.
PPT Slide
Lager Image
converges to σ 0 Gi in the sense of finite dimensional distributions, as M → ∞ and N → ∞, where ,
PPT Slide
Lager Image
Proof . By Lemma 2 of [8] ,
PPT Slide
Lager Image
Here, GH ( k ) represents a stationary Gaussian process whose covariance function has the form τ ( k ) ∼ ck 2 H −2 and 1/2 < H < 1.
And, the covariance function of
PPT Slide
Lager Image
PPT Slide
Lager Image
where H = d + 1/2 , has the same form as ck 2 H −2 . Therefore,
PPT Slide
Lager Image
By Lemma 3.1, with
PPT Slide
Lager Image
PPT Slide
Lager Image
converge to
PPT Slide
Lager Image
Theorem 3.3.
PPT Slide
Lager Image
converges to σ 0 BH ( t ) in the sense of finite dimensional distributions, as T → ∞ and M → ∞, where ,
PPT Slide
Lager Image
Proof . Consider the partial sum of
PPT Slide
Lager Image
which converges to fractional Brownian motion { BH ( t ) : t R } in the sense of finite dimensional distributions by Theorem 3.2 . □
4. Estimation of the self-similarity and PSD of FARIMA
When d < 1/2, the FARIMA process is stationary and the covariance function of a FARIMA(0, d , 0) process with zero mean and unit variance Gaussian innovations has the form
PPT Slide
Lager Image
The covariance function of the generalized FARIMA( p, d, q ) processes with Gaussian innovations has additional short-term components but follows the same asymptotic relation as the covariance function as FARIMA(0, d , 0) processes. Hence, we consider FARIMA(0, d , 0) in terms of d = 0.3 and estimate the selfsimilarity parameter H .
The R/S method which was used by Taqqu and Willinger( [12 , 13] ) is one of the better known method. For a time series X = { Xi : i ≤ 1}, with partial sum
PPT Slide
Lager Image
and sample variance
PPT Slide
Lager Image
the R/S static, or the rescaled adjusted range, is given by
PPT Slide
Lager Image
For fractional gaussian noise,
PPT Slide
Lager Image
where, CH is positive and finite constant not depend on n .
The following Figure 1 and 2 illustrates simulated FARIMA process and autocorrelation function with d = 0.3 in the case n = 200.
PPT Slide
Lager Image
Simulated FARIMA(0, 0.3, 0), n = 1, 000
PPT Slide
Lager Image
Autocorrelation Function
To determine H using the R/S statistic, proceed as follows. For a time series of length N , subdivide the series into blocks. Then, for each lag n , compute R ( n )/ S ( n ). Choosing logarithmically spaced values of n , plot log [ R ( n )/ S ( n )] versus log( n ) and get, for each n , several points on the plot. The spectrum density of a FARIMA( p, d, q ) process is equal to
PPT Slide
Lager Image
In Figure 3 , we estimate H as 0.830126 by calculating the R/S statistic and Figure 4 display power spectrum density of FARIMA process with d = 0.3.
PPT Slide
Lager Image
Estimating H
PPT Slide
Lager Image
Power Spectrum Density
BIO
Joo-Mok Kim recieved his Ph.D in Department of Mathematics from University of Utah in 1993 under the direction of Professor J. D. Mason. Since 1995, he has been at the Semyung University as a Professor. His research interests focus on the stochastic process, in particular, self-similar process, stable process and related application fields.
School of General Education, Semyung University, Jecheon 390-711, Korea.
E-mail:jmkim@semyung.ac.kr
Yun-Kyong Kim received his Ph.D degree in Department of Mathematics from Korea University in 1988 under the direction of Professor In-Suk Wee. From 1989 to 2002, he was a professor in Dept. of Mathematics, Dongshin University. Since 2002, he has been a professor in Department of Information and Communication Engineering, Dongshin University. His research interests center on Probability Theory and Stochastic Processes, in particular, Limit Theorems of Fuzzy Set Valued Random Variables.
Department of Information and Communication Engineering, Donghin University, Naju 520-714, Korea.
Email:ykkim@dsu.ac.kr
References
Duffield N.G. , O’Connell N. (1995) Large daviations and overflow probabilities for the general single-server queue with applications Math. Proc. Com. Phil. Soc. 118 363 - 374    DOI : 10.1017/S0305004100073709
Garrett M. , Willinger W. Analysis, modeling and generation of self similar vbr video traffic in Proceedings SIGCOMM’94 August 1994 269 - 280
Laskin N. , Lambadaris I. , Harmantzis F. , Devetsikiotis M. Fractional Levy Motions and its application to Network Traffic Modeling, Submitted.
Lopez-Ardao J.C. , Argibay-Losada P. , Rodriguez-Rubio R.F. 2004 On Modeling MPEG Vido at the Frame Level Using Self-similar Processes, MIPS 2004 37 - 48
Rabinovitch P. 2000 Statistical estimation of effective bandwidth, Information and System Sciences
Samorodnitsky G. , Taqqu M. S. 1994 Stable non-Gaussian processes: Stochastic models with Infinite Variance Chapman and Hall New York, London
Sheluhin O.I. , Smolskiy S.M. , Osin A.V. 2007 Self-Similar Processes in Telecomunications J.Wiley and Sons
Sikdar B. , Vastola K.S. On the Convergence of MMPP and Fractional ARIMA processes with long-range dependence to Fractional Brownian motion Proc. of the 34th CISS Prinston, NJ 2000
Stark H. , Woods J.W. 2002 Probability and Random Processes with Applications to Signal Processing Prince Hall
Tan X. , Tan Z. , Fang W. Study of Network Traffic Analysis Model The 2013 AASRI Winter International Conference On Engineering and Technology
Taqqu M. S. , Teverovsky V. (1997) Robustness of Whittle-type estimators for time series with long-range dependence Stochastic Models 13 723 - 757    DOI : 10.1080/15326349708807449
Taqqu M. S. , Teverovsky V. 1996 On Estimating the intensity of long-range dependence in finite and infinte variance time series, A practical guide to heavy tails : Statistical Techniques for Analyzing heavy tailed distributions Birkhauser Boston
Taqqu M. S. , Teverovsky V. , Willinger W. (1995) Estimators for long-range dependence : Empirical study Fractals 3 785 - 798    DOI : 10.1142/S0218348X95000692
Taqqu M. S. , Willinger W. , Sherman R. (1997) Proof of a fundamental result in self-similar traffic modeling Computer Communication review 27 5 - 23    DOI : 10.1145/263876.263879