Back to Search
Start Over
An approximate likelihood function of spatial correlation parameters
- Source :
- Journal of the Korean Statistical Society. 45:276-284
- Publication Year :
- 2016
- Publisher :
- Springer Science and Business Media LLC, 2016.
-
Abstract
- Even under assumption of normality, likelihood-based inferences are often difficult for large and irregularly spaced spatial datasets. Exact calculations of the likelihood for a Gaussian spatial process observed in n locations require O ( n 3 ) operations. Instead of Whittle’s approximation to the Gaussian log likelihood for large spatial datasets, this paper introduces an approximated likelihood function of spatial parameters based on the correlogram, which involves no calculation of determinants and is computationally feasible. The proposed likelihood approximation method for spatial parameter is applied to the estimation of the spatial structure of changes in the average summer temperature based on 30 years of data by using an regional climate model (RCM) with a particular global climate model (GCM) boundary condition. The results verify the benefits and the performance of the proposed method.
- Subjects :
- Statistics and Probability
Spatial correlation
Restricted maximum likelihood
05 social sciences
Maximum likelihood sequence estimation
01 natural sciences
Marginal likelihood
010104 statistics & probability
Likelihood-ratio test
0502 economics and business
Statistics
Applied mathematics
0101 mathematics
Likelihood function
Spatial analysis
Correlogram
050205 econometrics
Mathematics
Subjects
Details
- ISSN :
- 12263192
- Volume :
- 45
- Database :
- OpenAIRE
- Journal :
- Journal of the Korean Statistical Society
- Accession number :
- edsair.doi...........9a2c08216e6935f171ba303bb4128bca