In a laboratory experiment, suppose that Yi is the ith observed (independent) yield associated with the dependent observational measurements xij, i = 1,2, ... , m; j = 1,2, ... , n. It is desired to determine a linear regression fit into these data points. Let bj, j = 0, 1, ... , n, be the regression coefficients. It is desired to determine all bj such that the sum of the absolute deviations between the observed and the estimated yields is minimized. Formulate the problem as a goal programming model.