?=================================================================== ? Method of moments estimation of a Normal-Gamma stochastic = ? frontier model = ? = ? User must define the data matrix with the following line: = ? = ? NAMELIST ; X = ... $ = ? = ? User's dependent variable is Y. Change the following line = ? = ? CREATE ; Y = the dependent variable $ = ?=================================================================== REGRESS ; Lhs = y ; Rhs = X ; Res = e $ CREATE ; e2 = e * e ; e3 = e2 * e ; e4 = e3 * e ; ai = e + b(1) $ CALC ; a = b(1) ; m2 = xbr(e2) ; m3 = xbr(e3) ; m4 = xbr(e4) $ MATRIX ; V = XVCM(ai,e2,e3,e4) $ WALD ; start = a,m2,m3,m4 ; var = V ; labels = at,m2t,m3t,m4t ; fn1 = -3 * m3t / (m4t-3 * m2t^2) ? é ; fn2 = 13.5 * m3t^4 / (m4t-3 * m2t^2)^3 ? P ; fn3 = m2t - 1.5 * m3t^2 / (m4t-3 * m2t^2) ? å2v ; fn4 = at + 4.5 * m3t^3 / (m4t-3 * m2t^2)^2 ? a ; fn5 = m3t ? skewness ; fn6 = (m4t-3*m2t^2) $ ? degree of excess.