MPE Mathematical Problems in Engineering 1563-5147 1024-123X Hindawi Publishing Corporation 10.1155/2014/231592 231592 Research Article Integer-Valued Moving Average Models with Structural Changes http://orcid.org/0000-0002-5735-3996 Yu Kaizhi 1 Zou Hong 2 Shi Daimin 1 Li Wuquan 1 Statistics School Southwestern University of Finance and Economics Chengdu 611130 China swufe.edu.cn 2 School of Economics Southwestern University of Finance and Economics Chengdu 611130 China swufe.edu.cn 2014 2172014 2014 02 03 2014 22 06 2014 07 07 2014 21 7 2014 2014 Copyright © 2014 Kaizhi Yu et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

It is frequent to encounter integer-valued time series which are small in value and show a trend having relatively large fluctuation. To handle such a matter, we present a new first order integer-valued moving average model process with structural changes. The models provide a flexible framework for modelling a wide range of dependence structures. Some statistical properties of the process are discussed and moment estimation is also given. Simulations are provided to give additional insight into the finite sample behaviour of the estimators.

1. Introduction

Integer-valued time series occur in many situations, often as counts of events in consecutive points of time, for example, the number of births at a hospital in successive months, the number of road accidents in a city in successive months, and big numbers even for frequently traded stocks. Integer-valued time series represent an important class of discrete-valued time series models. Because of the broad field of potential applications, a number of time series models for counts have been proposed in literature. McKenzie  introduced the first order integer-valued autoregressive, INAR(1), model. The statistical properties of the INAR(1) are discussed in McKenzie , Al-Osh and Alzaid . The model is further generalized to a pth-order autoregression, INAR(p), by Alzaid and Al-Osh  and Du and Li . The qth-order integer-valued moving average model, INMA(q), was introduced by Al-Osh and Alzaid  and in a slightly different form by McKenzie . Ferland et al.  proposed an integer-valued GARCH model to study overdispersed counts, and Fokianos and Fried , Weiß , and Zhu and Wang  made further studies. Györfi et al.  proposed a nonstationary inhomogeneous INAR(1) process, where the autoregressive type coefficient slowly converges to one. Bakouch and Ristić  introduced a new stationary integer-valued autoregressive process of the first order with zero truncated Poisson marginal distribution. Kachour and Yao  introduced a class of autoregressive models for integer-valued time series using the rounding operator. Kim and Park  proposed an extension of integer-valued autoregressive INAR models by using a signed version of the thinning operator. Zheng et al.  proposed a first order random coefficient integer-valued autoregressive model and got its ergodicity, moments, and autocovariance functions of the process. Gomes and Canto e Castro  presented a random coefficient autoregressive process for count data based on a generalized thinning operator. Existence and weak stationarity conditions for these models were established. A simple bivariate integer-valued time series model with positively correlated geometric marginals based on the negative binomial thinning mechanism was presented by Ristić et al. , and some properties of the model are also considered. Pedeli and Karlis  considered a bivariate INAR(1) (BINAR(1)) process where cross correlation is introduced through the use of copulas for the specification of the joint distribution of the innovations.

Structural changes in economic data frequently correspond to instabilities in the real world. However, most work in this area has been concentrated on models without structural changes. It seems that the integer-valued autoregressive moving average (INARMA) model with break point has not attracted too much attention. For instance, a new method for modelling the dynamics of rain sampled by a tipping bucket rain gauge was proposed by Thyregod et al. . The models take the autocorrelation and discrete nature of the data into account. First order, second order, and threshold models are presented together with methods to estimate the parameters of each model. Monteiro et al.  introduced a class of self-exciting threshold integer-valued autoregressive models driven by independent Poisson-distributed random variables. Basic probabilistic and statistical properties of this class of models were discussed. Moreover, parameter estimation was also addressed. Hudecová  suggested a procedure for testing a change in the autoregressive models for binary time series. The test statistic is a maximum of normalized sums of estimated residuals from the model, and thus it is sensitive to any change which leads to a change in the unconditional success probability. Structural change is a statement about parameters, which only have meaning in the context of a model. In our discussion, we will focus on structural change in the simple count data model, the first order integer-valued moving average model, whose coefficient varies with the value of innovation. One of the leading reasons is that piecewise linear functions can offer a relatively simple approximation to the complex nonlinear dynamics.

The rest of this paper is divided into four sections. In Section 2, we give the definition and basic properties of the new INMA(1) model with structural changes. Section 3 discusses the estimation of the unknown parameters. We test the accuracy of the estimation via simulations in Section 4. Section 5 includes some concluding remarks.

2. Definition and Basic Properties Definition 1.

Let {Xt} be a process with state space N0; let 0<αi<1, i=1,,m, and τi, i=1,,m-1, be positive integers. The process {Xt} is said to be first order integer-valued moving average model with structural change (INMASC(1)) if Xt satisfies the following equation: (1)Xt={α1εt-1+εt,for  τ0εt-1τ1α2εt-1+εt,for  τ1<εt-1τ2vvvvvvvαm-1εt-1+εt,for  τm-2<εt-1τm-1αmεt-1+εt,for  τm-1<εt-1<τm, where {εt} is a sequence of independent and identically distributed Poisson random variables with mean λ and τ0=0, τm=.

The aim of this section is to provide expressions for the moments and stationary of INMASC(1) model. For this purpose, we introduce the following notations: (2)pi=P(τi-1<εtτi),ui=E(τi-1<εt-1τi),σi2=Var(τi-1<εt-1τi),qi=1-pi,It-1,i={1,if  τi-1<εt-1τi0,otherwise,i=1,,m.

Theorem 2.

The numerical characteristics of {Xt} are as follows: (3)(i)μX=E(Xt)=i=1mpiαiui+λ,(ii)σX2=Var(Xt)=i=1mpiαi[αi(ui2+σi2)+(1-αi)ui]-(i=1mpiαiui)2+λ,(iii)  γX(k)=cov(Xt,Xt-k)={i=1mpiαi(ui2+σi2-λui),k=10,k2.

Proof.

(i) It is easy to get the mean and variance of Xt by using the law of iterated expectations: (4)E(Xt)=E[It-1,1(α1εt-1)++It-1,m(αmεt-1)+εt]=E{E[It-1,1(α1εt-1)vviiiiv++It-1,m(αmεt-1)εt-1]}+E(εt)=α1E(It-1,1εt-1)++αmE(It-1,mεt-1)+E(εt)=i=1mpiαiui+λ.

(ii) Moreover, (5)Var(Xt)=Var(It-1,1(α1εt-1)++It-1,m(αmεt-1)+εt)=i=1mVar(It-1,i(αiεt-1))+Var(εt)+2i<jcov(It-1,i(αiεt-1),It-1,j(αjεt-1))=i=1m{Var(E[It-1,i(αiεt-1)εt-1])vv+E(Var[It-1,i(αiεt-1)εt-1])}+λ+2i<j{E[It-1,i(αiεt-1)It-1,j(αjεt-1)]vvvvvv-2E[It-1,i(αiεt-1)]E[It-1,j(αjεt-1)]}=i=1m[αi2Var(It-1,iεt-1)+αi(1-αi)E(It-1,iεt-1)]+λ-2i<jE{E[It-1,i(αiεt-1)εt-1]}vvvvvv×E{E[It-1,j(αjεt-1)εt-1]}=i=1m{[αi2E(It-12εt-12)-E2(It-1,iεt-1)]vv+piαi(1-αi)uiαi2E(It-12εt-12)-E2(It-1,iεt-1)}+λ-2i<jαiαjE(It-1,iεt-1)E(It-1,jεt-1)=i=1m{[piαi2(ui2+σi2)-pi2αi2ui2]+piαi(1-αi)ui}+λ-2i<jpiαiuipjαjuj=i=1mpiαi[αi(ui2+σi2)+(1-αi)ui]-(i=1mpiαiui)2+λ.

(iii) Note the correlation between αiεt-1 and εt-1; we have (6)cov(Xt,Xt-1)=cov(i=1mIt-1,i(αiεt-1)+εt,j=1mIt-2,j(αjεt-2)+εt-1)=i=1mcov(It-1,i(αiεt-1)+εt,εt-1)=i=1m{E[It-1,i(αiεt-1)εt-1]-E[It-1,i(αiεt-1)]E(εt-1)}=i=1m{E[E(It-1,i(αiεt-1)εt-1εt-1)]vv-E[E(It-1,i(αiεt-1)εt-1)]E(εt-1)}=i=1mαi[E(It-1,iεt-12)-λαiE(It-1,iεt-1)]=i=1mpiαi(ui2+σi2-λui).

Theorem 3.

Let Xt be the process defined by the equation in (1); then the {Xt} is a covariance stationary process.

Proof.

Both the unconditional mean and the unconditional variance of the {Xt} are finite constant. And the autocovariance function does not change with time. Thus {Xt}  is a stationary process.

Theorem 4.

Suppose {Xt} is INMASC(1) process. Then

T(X--μX)LN(0,σX2+2γX(1));

E(XtkIt-1,i=1)<, k=1,2,3,i=1,,m.

Proof.

(i) From definition and Theorem 2, we have that (X1,,Xi) and (Xj,Xj+1,) are independent whenever j-i>1. According to Theorem 9.1 of DasGupta , the process {Xt} is a stationary 1-dependent sequence. Therefore we can complete the proof.

(ii) For k=1, it follows that (7)E(Xt)max{E[It-1,i(αiεt-1)+εt],i=1,,m}max{E(αiεt-1)+E(εt),i=1,,m}λ(αmax+1)<,αmax=max(α1,,αm). For k=2, (8)E(Xt2)max{E[It-1,i(αiεt-1)+εt]2,i=1,,m}=max{E[It-i,1(αiεt-1)]2+E(εt2)vvvvv+2E[It-i,1(αiεt-1)εt],i=1,,mE[It-i,1(αiεt-1)]2}max{E[(αiεt-1)]2+E(εt2)vvvv+2E[(αiεt-1)εt],i=1,,mE[(αiεt-1)]2}=max{[(λ+λ2)αi2+λαi(1-αi)]vvvv+(λ+λ2)+λ2αi,i=1,,m}2(λ+λ2)αmax+0.25λ+λ2αmax<. For k=3, (9)E(Xt3)max{E[It-1,i(αiεt-1)+εt]3,i=1,,m}=max{E[It-1,i(αiεt-1)]3+E(εt3)vvvv+3E[It-1,i2(αiεt-1)2εt]vvvv+3E[It-1,i(αiεt-1)εt2],i=1,,m[It-1,i(αiεt-1)]3}max{E(αiεt-1)3+E(εt3)+3E[(αiεt-1)2εt]vvvv+3E[(αiεt-1)εt2],i=1,,mE(αiεt-1)3+E(εt3)+3E[(αiεt-1)2εt]}max{[αi3τ1+3αi2(1-αi)τ2vvvvv+(αi-3αi2(1-αi)-αi3)λ]vvvv+τ1+3{[αi2τ2+αi(1-αi)λ]λ}vvvv+3λαiτ2,i=1,,mαi3τ1+3αi2}λαmax[αmax2(τ1-1-3λ)vvvvvv+3τ2(αmax+1)+3λ+1αmax2]+τ1<, where τ1:=λ3+3λ2+λ, τ2:=λ2+λ, and αmax=max(α1,,αm). Then note that E(Xtk)< implies E(XtkIt-1,i=1)< for k=1,2,3, i=1,2,,m.

Theorem 5.

Let {Xt} be a INMASC(1) process according to Definition 1. Let X- be the sample mean of {Xt}; then the stochastic process {Xt} is ergodic in the mean.

Proof.

Since γX(k)0, k.

From Theorem 7.1.1 in Brockwell and Davis , we get (10)Var(X-T)=E(X-T-μX)20. Then X-T converges in probability to μX. Therefore, the process {Xt} is ergodic in the mean.

Theorem 6.

Suppose {Xt} is a INMASC(1) process; then (11)P(|γ^X(k)-γX(k)|ε)P0, where γ^X(k)=(1/T)t=1T-k(Xt+k-X-T)(Xt-X-T).

The proof of Theorem 6 is similar to Theorem 4 given in Yu et al. . It is easy to verify; we skip the details.

3. Estimation of Parameters

In this paper, we consider one method, namely, moment estimation. An advantage of the method is that it is simple and often produces good results. The estimation problem of INMASC(1) parameters is complex. In fact, for the INMASC(1) processes, the conditional distribution of the Xt given εt-1 is the convolution of the distribution of the arrival process εt and one thinning operation αiεt-1. On the other hand, there are too many unknown parameters of the model, such as λ, αi, pi, ui, and σi2, i=1,,m, whereas the number of moment conditions is small.

Therefore we cannot estimate all the parameters unless additional assumptions are made. Then, we assume that the number of break point m is two and assume that the value of break point τi, i=1,,m, and the mean of innovation λ are also known. Thus, here we estimate INMASC(1) model with two break points. Under these assumptions, all the parameters λ, pi, ui, and σi2, i=1,2,3, are known. We only need to estimate the autoregressive coefficients α1, α2, and α3. Using the sample mean and sample covariance function, we can get the moment estimators via solving the following equations: (12)γ^(0)=i=13piαi[αi(ui2+σi2)+(1-αi)ui]-(i=13piαiui)2+λγ^(1)=i=13piαi(ui2+σi2-λui)X-=i=13piαiui+λ. If you want to estimate all parameters, you can use GMM method based on probability generating functions introduced by BräKnnäK and Hall . But they found covariance matrix of estimators depends on z and the orders besides the model parameters in a highly complex way. Thus we do not use this method here. In next section, simulations are provided to give insight into the finite sample behaviour of these estimators.

4. Simulation Study

Consider the following INMASC(1) model: (13)Xt={α1εt-1+εt,for  εt-1τ1α2εt-1+εt,for  τ1<εt-1τ2α3εt-1+εt,for  τ2<εt-1, where {εt} is a sequence of i.i.d. For fixed t, εt follows a Poisson distribution with mean λ.

The parameters values considered in this model are listed as follows:

(model  A) (α1,α2,α3)=(0.1,0.1,0.1), with τ1=3, τ2=10, λ=1;

(model  B) (α1,α2,α3)=(0.2,0.3,0.1), with τ1=8, τ2=17, λ=10;

(model  C) (α1,α2,α3)=(0.4,0.3,0.1), with τ1=21, τ2=43, λ=50.

We use the above models to generate data and then use moment methods to estimate the parameters. We computed the empirical bias and the mean square error (MSE) based on 300 replications for each parameter combination. These values are reported within parenthesis in Table 1.

Bias and mean square error for models A, B, and C.

Model Parameter Sample size
50 200 500
A α 1 0.0267(0.3948) 0.0097(0.0753) 0.0034(0.0453) BiasMSE
α 2 0.0645(0.4731) 0.0115(0.1314) 0.0025(0.0376) BiasMSE
α 3 0.0417(0.2908) 0.0083(0.0811) 0.0046(0.0342) BiasMSE

B α 1 0.0335(0.4623) 0.0127(0.1803) 0.0036(0.0745) BiasMSE
α 2 0.0297(0.2806) 0.0103(0.3449) 0.0054(0.0847) BiasMSE
α 3 0.0251(0.3408) 0.0081(0.0372) 0.0024(0.0165) BiasMSE

C α 1 0.0736(1.0435) 0.0178(0.3562) 0.0068(0.0357) BiasMSE
α 2 0.0582(0.4127) 0.0215(0.0433) 0.0049(0.0212) BiasMSE
α 2 0.0237(0.3205) 0.0081(0.0547) 0.0031(0.0274) BiasMSE

From the results in Table 1, we can see moment estimation is good estimation methods producing estimators whose bias and MSEs are small when the sample sizes are larger. In addition, this method is fast and easy to implement. It is perhaps not surprising that the MSEs are larger when these sample sizes are smaller. As to be expected, both the bias and the MSEs converge to zero with increasing sample size T.

5. Conclusion

Based on some limitations of the present count data models, a new INMA model is introduced to model structural changes. Expressions for mean, variance, and autocorrelation functions are given. Stationary and other basic statistical properties are also obtained. We derived moment estimators of the unknown parameters. Furthermore, we constructed several simulations to evaluate the performance of the estimators of model parameters.

Conflict of Interests

The authors declare that there is no conflict of interests regarding the publication of this paper

Acknowledgments

This work is supported by the National Natural Science Foundation of China (no. 71201126), the Science Foundation of Ministry of Education of China (no. 12XJC910001), and the Fundamental Research Funds for the Central Universities (nos. JBK140211 and JBK120405).

McKenzie E. Some simple models for discrete variate time series Water Resources Bulletin 1985 21 4 635 644 10.1111/j.1752-1688.1985.tb05378.x 2-s2.0-0022111048 McKenzie E. Autoregressive moving-average processes with negative-binomial and geometric marginal distributions Advances in Applied Probability 1986 18 3 679 705 10.2307/1427183 MR857325 ZBL0603.62100 Al-Osh M. A. Alzaid A. A. First order integer-valued autoregressive INAR(1) process Journal of Time Series Analysis 1987 8 3 261 275 10.1111/j.1467-9892.1987.tb00438.x MR903755 Alzaid A. A. Al-Osh M. An integer-valued pth-order autoregressive structure INAR(p) process Journal of Applied Probability 1990 27 2 314 324 10.2307/3214650 MR1052303 Du J. G. Li Y. The integer-valued autoregressive (INAR(p)) model Journal of Time Series Analysis 1991 12 2 129 142 10.1111/j.1467-9892.1991.tb00073.x MR1108796 Al-Osh M. Alzaid A. A. Integer-valued moving average (INMA) process Statistical Papers 1988 29 4 281 300 10.1007/BF02924535 MR1000749 2-s2.0-0003559496 McKenzie E. Some ARMA models for dependent sequences of Poisson counts Advances in Applied Probability 1988 20 4 822 835 10.2307/1427362 MR968000 Ferland R. Latour A. Oraichi D. Integer-valued GARCH process Journal of Time Series Analysis 2006 27 6 923 942 10.1111/j.1467-9892.2006.00496.x MR2328548 2-s2.0-33745955479 Fokianos K. Fried R. Interventions in INGARCH processes Journal of Time Series Analysis 2010 31 3 210 225 10.1111/j.1467-9892.2010.00657.x MR2676152 2-s2.0-77953417495 Weiß C. H. The INARCH(1) model for overdispersed time series of counts Communications in Statistics: Simulation and Computation 2010 39 6 1269 1291 10.1080/03610918.2010.490317 MR2785642 Zhu F. A negative binomial integer-valued GARCH model Journal of Time Series Analysis 2011 32 1 54 67 10.1111/j.1467-9892.2010.00684.x MR2790672 2-s2.0-78650045133 Zhu F. Modeling overdispersed or underdispersed count data with generalized Poisson integer-valued GARCH models Journal of Mathematical Analysis and Applications 2012 389 1 58 71 10.1016/j.jmaa.2011.11.042 MR2876481 2-s2.0-84855822597 Zhu F. Wang D. Diagnostic checking integer-valued ARCH(p) models using conditional residual autocorrelations Computational Statistics and Data Analysis 2010 54 2 496 508 10.1016/j.csda.2009.09.019 ZBL05689605 2-s2.0-70350567862 Györfi L. Ispány M. Pap G. Varga K. Poisson limit of an inhomogeneous nearly critical INAR(1) model Acta Universitatis Szegediensis 2007 73 3-4 789 815 MR2380077 Bakouch H. S. Ristić M. M. Zero truncated Poisson integer-valued AR(1) model Metrika 2010 72 2 265 280 10.1007/s00184-009-0252-5 MR2725101 2-s2.0-77956913129 Kachour M. Yao J. F. First-order rounded integer-valued autoregressive ((RINAR(1)) process Journal of Time Series Analysis 2009 30 4 417 448 10.1111/j.1467-9892.2009.00620.x MR2536061 2-s2.0-67650673066 Kim H.-Y. Park Y. A non-stationary integer-valued autoregressive model Statistical Papers 2008 49 3 485 502 10.1007/s00362-006-0028-1 MR2399216 2-s2.0-42449147938 Zheng H. Basawa I. V. Datta S. First-order random coefficient integer-valued autoregressive processes Journal of Statistical Planning and Inference 2007 137 1 212 229 10.1016/j.jspi.2005.12.003 MR2292852 ZBL1098.62117 2-s2.0-33748435458 Gomes D. Canto e Castro L. Generalized integer-valued random coefficient for a first order structure autoregressive (RCINAR) process Journal of Statistical Planning and Inference 2009 139 12 4088 4097 10.1016/j.jspi.2009.05.037 MR2558352 2-s2.0-69249208468 Ristić M. M. Nastić A. S. Jayakumar K. Bakouch H. S. A bivariate INAR(1) time series model with geometric marginals Applied Mathematics Letters 2012 25 3 481 485 10.1016/j.aml.2011.09.040 MR2856018 2-s2.0-80955150847 Pedeli X. Karlis D. A bivariate INAR(1) process with application Statistical Modelling 2011 11 4 325 349 Thyregod P. Carstensen J. Madsen H. Arnbjerg-Nielsen K. Integer valued autoregressive models for tipping bucket rainfall measurements Environmetrics 1999 10 4 395 411 10.1002/(SICI)1099-095X(199907/08)10:4<395::AID-ENV364>3.0.CO;2-M 2-s2.0-0032855974 Monteiro M. Scotto M. G. Pereira I. Integer-valued self-exciting threshold autoregressive processes Communications in Statistics: Theory and Methods 2012 41 15 2717 2737 10.1080/03610926.2011.556292 MR2946642 2-s2.0-84862648346 Hudecová Š. Structural changes in autoregressive models for binary time series Journal of Statistical Planning and Inference 2013 143 10 1744 1752 10.1016/j.jspi.2013.05.009 MR3082230 2-s2.0-84881218456 DasGupta A. Asymptotic Theory of Statistics and Probability 2008 New York, NY, USA Springer MR2664452 Brockwell P. J. Davis R. A. Time Series: Theory and Methods 1991 New York, NY, USA Springer 10.1007/978-1-4419-0320-4 MR1093459 Yu K. Shi D. Zou H. The random coefficient discretevalued time series model Statistical Research 2011 28 4 106 112 BräKnnäK K. Hall A. Estimation in integer-valued moving average models Applied Stochastic Models in Business and Industry 2001 17 3 277 291 10.1002/asmb.445 MR1864091 2-s2.0-0035387571