Computational Science and Techniques (Mar 2013)
Baltic sea algae analysis using Bayesian spatial statistics methods
Abstract
Spatial statistics is one of the fields in statistics dealing with spatialy spread data analysis. Recently, Bayes methods are often applied for data statistical analysis. A spatial data model for predicting algae quantity in the Baltic Sea is made and described in this article. Black Carrageen is a dependent variable and depth, sand, pebble, boulders are independent variables in the described model. Two models with different covariation functions (Gaussian and exponential) are built to estimate the best model fitting for algae quantity prediction. Unknown model parameters are estimated and Bayesian kriging prediction posterior distribution is computed in OpenBUGS modeling environment by using Bayesian spatial statistics methods.