Fast estimation of matrix exponential spatial models

The matrix exponential spatial specification (MESS) is an alternative to the autoregressive-type (SAR-type) specifications with several attractive properties. dependence in MESS-type models formulated through a term, and estimation of these may require computation terms many times procedure. In literature, it well documented that can pose challenges reliability, stability, accuracy, efficiency. We propose matrix-vector products approach based on truncation Taylor series expansion for fast models. show how efficiently implement this first-order MESS model, provide extensive simulation evidence its computational advantage over default method utilized by popular statistical software.