Bivariate copula in fitting rainfall data
The usage of copula to determine the joint distribution between two variables is widely used in various areas. The joint distribution of rainfall characteristic obtained using the copula model is more ideal than the standard bivariate modelling where copula is belief to have overcome some limitation...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
American Institute of Physics Inc.
2014
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/52020/ http://dx.doi.org/10.1063/1.4887724 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Malaysia |
| Summary: | The usage of copula to determine the joint distribution between two variables is widely used in various areas. The joint distribution of rainfall characteristic obtained using the copula model is more ideal than the standard bivariate modelling where copula is belief to have overcome some limitation. Six copula models will be applied to obtain the most suitable bivariate distribution between two rain gauge stations. The copula models are Ali-Mikhail-Haq (AMH), Clayton, Frank, Galambos, Gumbel-Hoogaurd (GH) and Plackett. The rainfall data used in the study is selected from rain gauge stations which are located in the southern part of Peninsular Malaysia, during the period from 1980 to 2011. The goodness-of-fit test in this study is based on the Akaike information criterion (AIC). |
|---|