Sparse estimates in GLM with environmental application
|Year of publication
|MU Faculty or unit
|We give some minimal theoretical background of the sparse estimation technique based on the four-step Basis Pursuit Algorithm (BPA4) and sketch briefly its steps. The new concept is illustrated by two application examples: (1) simulation study proving better numerical stability in contrast with standard estimation methods, (2) strongly rank-deficient environmental GLM of air pollution by suspended particulate matter.