A non-linear integer-valued autoregressive model with zero-inflated data series

被引:0
作者
Popovic, Predrag M. [1 ]
Bakouch, Hassan S. [2 ]
Ristic, Miroslav M. [3 ]
机构
[1] Univ Nis, Fac Civil Engn & Architecture, Nish, Serbia
[2] Qassim Univ, Coll Sci, Dept Math, Buraydah, Saudi Arabia
[3] Univ Nis, Fac Sci & Math, Nish, Serbia
关键词
INAR(1) model; non-linear model; time series; simulation; generalized zero-modified geometric thinning operator; stationarity; GEOMETRIC INAR(1) PROCESS; TIME-SERIES; POISSON; UNDERDISPERSION; EQUIDISPERSION; COUNT;
D O I
10.1080/02664763.2024.2419495
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
A new non-linear stationary process for time series of counts is introduced. The process is composed of the survival and innovation component. The survival component is based on the generalized zero-modified geometric thinning operator, where the innovation process figures in the survival component as well. A few probability distributions for the innovation process have been discussed, in order to adjust the model for observed series with the excess number of zeros. The conditional maximum likelihood and the conditional least squares methods are investigated for the estimation of the model parameters. The practical aspect of the model is presented on some real-life data sets, where we observe data with inflation as well as deflation of zeroes so we can notice how the model can be adjusted with the proper parameter selection.
引用
收藏
页码:1195 / 1218
页数:24
相关论文
共 37 条
[1]  
AlOsh A, 1987, J TIME SER ANAL, P261, DOI DOI 10.1111/J.1467-9892.1987.TB00438.X
[2]  
Alzaid A. A., 1988, Statistica Neerlandica, V42, P53, DOI DOI 10.1111/J.1467-9574.1988.TB01521.X
[3]   AN INTEGER-VALUED PTH-ORDER AUTOREGRESSIVE STRUCTURE (INAR(P)) PROCESS [J].
ALZAID, AA ;
ALOSH, M .
JOURNAL OF APPLIED PROBABILITY, 1990, 27 (02) :314-324
[4]   A Zero-Inflated Geometric INAR(1) Process with Random Coefficient [J].
Bakouch, Hassan S. ;
Mohammadpour, Mehrnaz ;
Shirozhan, Masumeh .
APPLICATIONS OF MATHEMATICS, 2018, 63 (01) :79-105
[5]   A generalised NGINAR(1) process with inflated-parameter geometric counting series [J].
Borges, Patrick ;
Bourguignon, Marcelo ;
Molinares, Fabio Fajardo .
AUSTRALIAN & NEW ZEALAND JOURNAL OF STATISTICS, 2017, 59 (01) :137-150
[6]   A geometric time series model with inflated-parameter Bernoulli counting series [J].
Borges, Patrick ;
Molinares, Fabio Fajardo ;
Bourguignon, Marcelo .
STATISTICS & PROBABILITY LETTERS, 2016, 119 :264-272
[7]   Extended Poisson INAR(1) processes with equidispersion, underdispersion and overdispersion [J].
Bourguignon, Marcelo ;
Rodrigues, Josemar ;
Santos-Neto, Manoel .
JOURNAL OF APPLIED STATISTICS, 2019, 46 (01) :101-118
[8]   A new geometric INAR(1) process based on counting series with deflation or inflation of zeros [J].
Bourguignon, Marcelo ;
Borges, Patrick ;
Molinares, Fabio Fajardo .
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2018, 88 (17) :3338-3348
[9]   An INAR(1) process for modeling count time series with equidispersion, underdispersion and overdispersion [J].
Bourguignon, Marcelo ;
Weiss, Christian H. .
TEST, 2017, 26 (04) :847-868
[10]   A simple integer-valued bilinear time series model [J].
Doukhan, P ;
Latour, A ;
Oraichi, D .
ADVANCES IN APPLIED PROBABILITY, 2006, 38 (02) :559-578