出版社：Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of University of Latvia
摘要：Geoid/quasi-geoid modelling in a local (small) area is often made with polynomials. The
optimal version of a polynomial is found by testing its successive versions using different statistical
parameters, i.e. with different degree and number of coefficients. In this publication, the authors
presented 3 approaches to search for an optimal version of the polynomial. Two of them were based
on one of the robust estimation methods, i.e. the Danish method. Therefore, the question arises
whether this method is suitable for this type of work.
The publication analyses 6 different methods of robust estimation and the method of least
squares. The control parameters of the methods were selected in such a way as to obtain a comparable
accuracy of fitting the polynomial into the points each time. Then, the actual accuracy obtained for
each of them was compared. The result of the study is a ranking of methods in terms of the most
accurate fitting results.
关键词：geodesy; geoscience; detection algorithms; numerical analysis; geoid; model selection
criteria
