Search

Your search keyword '"Popović, Predrag M."' showing total 14 results
Start Over Author "Popović, Predrag M."
14 results on '"Popović, Predrag M."'

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

Author

Popović, Predrag M., Bakouch, Hassan S., and Ristić, Miroslav M.

Subjects
*STATIONARY processes, *TIME series analysis, *NONLINEAR operators, *AUTOREGRESSIVE models, *DISTRIBUTION (Probability theory)
Abstract

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. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

8. Forecasting with two generalized integer-valued autoregressive processes of order one in the mutual random environment

Author

Popović, Predrag M., Laketa, Petra N., and Nastić, Aleksandar S.

Subjects
62 Statistics::62M Inference from stochastic processes [Classificació AMS], Matemàtiques i estadística::Estadística matemàtica [Àrees temàtiques de la UPC], Time series of count, Non-stationary process, Negative binomial thinning, Random states, INAR
Abstract

In this article, we consider two univariate random environment integer-valued autoregressive processes driven by the same hidden process. A model of this kind is capable of describing two correlated non-stationary counting time series using its marginal variable parameter values. The properties of the model are presented. Some parameter estimators are described and implemented on the simulated time series. The introduction of this bivariate integer-valued autoregressive model with a random environment is justified at the end of the paper, where its real-life data-fitting performance was checked and compared to some other appropriate models. The forecasting properties of the model are tested on a few data sets, and forecasting errors are discussed through the residual analysis of the components that comprise the model.

Published
2019

11. INAR(1) process with weighted negative binomial Lindley distributed innovations and applications to criminal and COVID-19 data.

Author

Mohammadi, Zohreh, Bakouch, Hassan S., and Popović, Predrag M.

Abstract

AbstractIn this study, we introduce a pliant stationary first-order integer-valued autoregressive (INAR) process with weighted negative binomial Lindley innovations. The main properties of the model are derived. The methods of conditional maximum likelihood, conditional least square and Yule-Walker are used for estimating the process parameters, while the efficiency of these three methods is evaluated through a simulation study. Finally, the practical aspect of the proposed INAR(1) process is discussed on two time series of the monthly number of criminal mischief reports in Pittsburgh and the daily COVID-19 death cases in Paraguay. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

14. RANDOM COEFFICIENT BIVARIATE INAR(1) PROCESS.

Author

Popović, Predrag M.

Subjects
*BIVARIATE analysis, *AUTOREGRESSIVE models, *AUTOREGRESSION (Statistics), *POISSON distribution, *BIG data
Abstract

A bivariate autoregressive model for time series of counts is presented. The model is composed of survival and innovation components. The dependence between series is achieved through innovation parts. The autoregression is modelled with the survival component which is based on the binomial thinning operator. The coefficients that figure here are random variables. Statistical properties of the model are presented. The existence, stationarity and ergodicity of the model is proved. We focus on the model where the innovation components follow bivariate Poisson distribution. We suggest conditional maximum likelihood and the method of moments for parameters estimation. Both methods are tested on simulated data sets. [ABSTRACT FROM AUTHOR]

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results