三阶段DEA，在SFA回归后有一个LR test of the one-sided error检验，如果通过不了需要怎么调整，大家帮忙个点建议啊，是需要改环境变量还是要调整指标体系。我的样本9个，投入产出各2个，是不是样本量太小的原因。
the final mle estimates are :
                 coefficient     standard-error    t-ratio
  beta 0        -0.28404642E+03  0.44548294E+01 -0.63761458E+02
  beta 1         0.91432282E+03  0.41626073E+01  0.21965147E+03
  beta 2        -0.16452175E+03  0.10734166E+02 -0.15326924E+02
  beta 3         0.23200658E+03  0.32099629E+01  0.72277029E+02
  beta 4        -0.95813368E+03  0.25490382E+01 -0.37588047E+03
  sigma-squared  0.13822947E+07  0.10000003E+01  0.13822943E+07
  gamma          0.99999808E+00  0.12717180E-04  0.78633633E+05
   mu is restricted to be zero
   eta is restricted to be zero
log likelihood function =  -0.70737929E+02
LR test of the one-sided error =   0.35253034E+01
with number of restrictions = 1
[note that this statistic has a mixed chi-square distribution]