Zero‐Modified Geometric INAR(1) Process for Modelling Count Time Series with Deflation or Inflation of Zeros

type="main" xml:id="jtsa12131-abs-0001"> In this article, we propose a first-order integer-valued autoregressive [INAR(1)] process for dealing with count time series with deflation or inflation of zeros. The proposed process has zero-modified geometric marginals and contains the geometric INAR(1) process as a particular case. The proposed model is also capable of capturing underdispersion and overdispersion, which sometimes are caused by deflation or inflation of zeros. We explore several statistical and mathematical properties of the process, discuss point estimation of the parameters and find the asymptotic distribution of the proposed estimators. We also propose a test based on our model for checking if the count time series considered is deflated or inflated of zeros. Two empirical illustrations are presented in order to show the potential for practice of our zero-modified geometric INAR(1) process. This article contains a Supporting Information.

[1]  Dag Tjøstheim,et al.  Consistent Estimates for the Near(2) and Nlar(2) Time Series Models , 1988 .

[2]  Christian H. Weiß,et al.  Binomial AR(1) processes: moments, cumulants, and estimation , 2013 .

[3]  E. McKenzie,et al.  Some ARMA models for dependent sequences of poisson counts , 1988, Advances in Applied Probability.

[4]  Brendan McCabe,et al.  Forecasting discrete valued low count time series , 2004 .

[5]  Hassan S. Bakouch,et al.  A new geometric first-order integer-valued autoregressive (NGINAR(1)) process , 2009 .

[6]  B. McCabe,et al.  Asymptotic properties of CLS estimators in the Poisson AR(1) model , 2005 .

[7]  Dimitris Karlis,et al.  Validation tests for the innovation distribution in INAR time series models , 2014, Comput. Stat..

[8]  Christian H. Weiß,et al.  Serial dependence and regression of Poisson INARMA models , 2008 .

[9]  Christian H. Weiß,et al.  Compound Poisson INAR(1) processes: Stochastic properties and testing for overdispersion , 2014, Comput. Stat. Data Anal..

[10]  Miroslav M. Ristić,et al.  A geometric time series model with dependent Bernoulli counting series , 2013 .

[11]  Maria Eduarda Silva,et al.  Additive outliers in INAR(1) models , 2012 .

[12]  Fw Fred Steutel,et al.  Discrete analogues of self-decomposability and stability , 1979 .

[13]  Brendan McCabe.  Conditional Least Squares Estimation of the Poisson Autoregressive Model , 2005 .

[14]  Antonio Canale,et al.  Bayesian nonparametric forecasting for INAR models , 2016, Comput. Stat. Data Anal..

[15]  A. Nastic,et al.  Some geometric mixed integer-valued autoregressive (INAR) models , 2012 .

[16]  M. D. Martínez-Miranda,et al.  Computational Statistics and Data Analysis , 2009 .

[17]  Christian H. Weiß,et al.  Integer-valued autoregressive models for counts showing underdispersion , 2013 .

[18]  Mohamed Alosh,et al.  FIRST‐ORDER INTEGER‐VALUED AUTOREGRESSIVE (INAR(1)) PROCESS , 1987 .

[19]  Emad-Eldin A. A. Aly,et al.  Explicit stationary distributions for some galton-watson processes with immigration , 1994 .

[20]  Christian H. Weiß,et al.  Jumps in binomial AR(1) processes , 2009 .

[21]  B. McCabe,et al.  Analysis of low count time series data by poisson autoregression , 2004 .

[22]  C. Lai,et al.  First‐order integer valued AR processes with zero inflated poisson innovations , 2012 .

[23]  Christian H. Weiß.  Controlling jumps in correlated processes of Poisson counts , 2009 .

[24]  A. Nastic.  On Shifted Geometric INAR(1) Models Based on Geometric Counting Series , 2012 .