Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties
Spatial modelling has its applications in many fields. In time-series there exist a class of models known as long memory models where the autocorrelation function decays rather slowly. These types of time-series data are modelled as fractionally integrated ARMA processes. Spatial data may also exhib...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis
2008
|
| _version_ | 1825944127937708032 |
|---|---|
| author | Shitana, Mahendran |
| author_facet | Shitana, Mahendran |
| author_sort | Shitana, Mahendran |
| collection | UPM |
| description | Spatial modelling has its applications in many fields. In time-series there exist a class of models known as long memory models where the autocorrelation function decays rather slowly. These types of time-series data are modelled as fractionally integrated ARMA processes. Spatial data may also exhibit a long memory structure and in order to model such a structure we introduce a new class of models called the fractionally integrated separable spatial autoregressive (FISSAR) model and discuss some of its properties. One way of estimating the parameters of the FISSAR model is also discussed in this article. |
| first_indexed | 2024-03-06T07:11:01Z |
| format | Article |
| id | upm.eprints-7026 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T07:11:01Z |
| publishDate | 2008 |
| publisher | Taylor & Francis |
| record_format | dspace |
| spelling | upm.eprints-70262010-06-02T02:30:34Z http://psasir.upm.edu.my/id/eprint/7026/ Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties Shitana, Mahendran Spatial modelling has its applications in many fields. In time-series there exist a class of models known as long memory models where the autocorrelation function decays rather slowly. These types of time-series data are modelled as fractionally integrated ARMA processes. Spatial data may also exhibit a long memory structure and in order to model such a structure we introduce a new class of models called the fractionally integrated separable spatial autoregressive (FISSAR) model and discuss some of its properties. One way of estimating the parameters of the FISSAR model is also discussed in this article. Taylor & Francis 2008 Article PeerReviewed Shitana, Mahendran (2008) Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties. Communications in Statistics: Theory and Methods, 37 (8). pp. 1266-1273. ISSN 1532-415X (online)/0361-0926 (print) http://dx.doi.org/10.1080/03610920701762762 10.1080/03610920701762762 English |
| spellingShingle | Shitana, Mahendran Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties |
| title | Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties |
| title_full | Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties |
| title_fullStr | Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties |
| title_full_unstemmed | Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties |
| title_short | Fractionally Integrated Separable Spatial Autoregressive (FISSAR) Model and Some of Its Properties |
| title_sort | fractionally integrated separable spatial autoregressive fissar model and some of its properties |
| work_keys_str_mv | AT shitanamahendran fractionallyintegratedseparablespatialautoregressivefissarmodelandsomeofitsproperties |