Estimation of nuisance parameters for inference based on least absolute deviations
Volume 22 / 1995
Applicationes Mathematicae 22 (1995), 515-529
DOI: 10.4064/am-22-4-515-529
Abstract
Statistical inference procedures based on least absolute deviations involve estimates of a matrix which plays the role of a multivariate nuisance parameter. To estimate this matrix, we use kernel smoothing. We show consistency and obtain bounds on the rate of convergence.
