An algorithm and Fortran program for multivariate LAD (\(\ell_1\) of \(\ell_2\)) regression (Q1614976)

A FORTRAN package is presented for multivariate least sum of absolute deviations (LAD) regression with respect to the \(\ell_1\) of \(\ell_2\) norm, and this regression method is compared with \(\ell_2\) of \(\ell_2\) regression and \(\ell_1\) of \(\ell_1\) regression. Applications of the algorithm include multivariate permutation analyses of experimental designs and prediction models which are based on Euclidean distance.