Likelihood Inference for Generalized Integer Autoregressive Time Series Models

Likelihood Inference for Generalized Integer Autoregressive Time Series Models

For modeling count time series data, one class of models is generalized integer autoregressive of order <i>p</i> based on thinning operators. It is shown how numerical maximum likelihood estimation is possible by inverting the probability generating function of the conditional distributi...

Full description

Bibliographic Details
Main Author: Harry Joe
Format: Article
Language:English
Published: MDPI AG 2019-10-01
Series:Econometrics
Subjects:
count time series
binomial thinning
thinning operators
compounding operation
self-generalized property
Online Access:https://www.mdpi.com/2225-1146/7/4/43
id doaj-7ebc7668e7014af8b54349f3ce77f44e
record_format Article
spelling doaj-7ebc7668e7014af8b54349f3ce77f44e2020-11-25T01:15:00ZengMDPI AGEconometrics2225-11462019-10-01744310.3390/econometrics7040043econometrics7040043Likelihood Inference for Generalized Integer Autoregressive Time Series ModelsHarry Joe0Department of Statistics, University of British Columbia, Vancouver, BC V6T 1Z4, CanadaFor modeling count time series data, one class of models is generalized integer autoregressive of order <i>p</i> based on thinning operators. It is shown how numerical maximum likelihood estimation is possible by inverting the probability generating function of the conditional distribution of an observation given the past <i>p</i> observations. Two data examples are included and show that thinning operators based on compounding can substantially improve the model fit compared with the commonly used binomial thinning operator.https://www.mdpi.com/2225-1146/7/4/43count time seriesbinomial thinningthinning operatorscompounding operationself-generalized property
collection DOAJ
language English
format Article
sources DOAJ
author Harry Joe
spellingShingle Harry Joe
Likelihood Inference for Generalized Integer Autoregressive Time Series Models
Econometrics
count time series
binomial thinning
thinning operators
compounding operation
self-generalized property
author_facet Harry Joe
author_sort Harry Joe
title Likelihood Inference for Generalized Integer Autoregressive Time Series Models
title_short Likelihood Inference for Generalized Integer Autoregressive Time Series Models
title_full Likelihood Inference for Generalized Integer Autoregressive Time Series Models
title_fullStr Likelihood Inference for Generalized Integer Autoregressive Time Series Models
title_full_unstemmed Likelihood Inference for Generalized Integer Autoregressive Time Series Models
title_sort likelihood inference for generalized integer autoregressive time series models
publisher MDPI AG
series Econometrics
issn 2225-1146
publishDate 2019-10-01
description For modeling count time series data, one class of models is generalized integer autoregressive of order <i>p</i> based on thinning operators. It is shown how numerical maximum likelihood estimation is possible by inverting the probability generating function of the conditional distribution of an observation given the past <i>p</i> observations. Two data examples are included and show that thinning operators based on compounding can substantially improve the model fit compared with the commonly used binomial thinning operator.
topic count time series
binomial thinning
thinning operators
compounding operation
self-generalized property
url https://www.mdpi.com/2225-1146/7/4/43
work_keys_str_mv AT harryjoe likelihoodinferenceforgeneralizedintegerautoregressivetimeseriesmodels
_version_ 1725155014824951808

Similar Items