Given training sample, the problem of classifying Gaussian spatial data into one of two populations specified by conditional autoregressive model (CAR) with different mean functions is considered. This paper concerns with classification procedures associated with Bayes Discriminant Function (BDF) under deterministic spatial sampling design. In the case of complete parametric certainty, the overall misclassification probability associated with aforementioned BDF is derived. This is the extension of the previous one to the CAR case. Spatial weights based on inverse of Euclidean distance and the second and third order neighbourhood schemes on regular 2-dimensional lattice are used for illustrative examples.
The effect of the spatial sampling design, Mahalanobis distances and prior probabilities on the performance of proposed classification procedure is numerically evaluated.
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.