A New Approximation: Gauss-Lanczos Approximated SAR Model Solution
In this chapter, a new approximate ML theory based solution for the SAR model which is called Gauss-Lanczos (GL) approximation is developed. The key idea of the proposed algorithm is to find only the some of the eigenvalues of a large matrix, instead of finding all the eigenvalues, by reducing the size of large matrix dramatically using GL algorithm . Because of this property of GL algorithm, we can save huge computation costs, especially when the matrix size is quite large.
KeywordsSpatial Autocorrelation Problem Size Chebyshev Polynomial Large Problem Size Large Matrix
Unable to display preview. Download preview PDF.