Klaipėdos universitetas

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.

Modern information technologies (IT) provide progressive tools and methods for data collection, storage, processing, and publication. The essence of historical research is to synthesize new information from different types of historical sources. The analysis of scientific publications proved that IT are still rarely applied to historical research. Several reasons may account for the state of things. One of them is related to rather conservative attitudes of researchers in the field of IT towards collaboration, which also accounts for the absence of specialized software for historical research. The article introduces IT tools and methods which can be used in historical research in a popular way, and the authors expect to promote interdisciplinarity in the field of history.