新手提问，希望有高手解答。拟合TGARCH模型，code如下：
/* Estimate Threshold Garch (TGARCH) Model */
   proc model data = indexsh;
      parms arch0 .1 arch1_plus .1 arch1_minus .1 garch1 .75 ;
      /* mean model */
      r_log= intercept ;
      /* variance model */
      if zlag(resid.r_log) < 0 then
         h.r_logr_log = (arch0 + arch1_plus*zlag(-resid.r_log) + garch1*zlag(sqrt(h.r_log)))**2 ;
      else
         h.r_log = (arch0 + arch1_minus*zlag(-resid.r_log) + garch1*zlag(sqrt(h.r_log)))**2 ;
      /* fit the model */
      fit r_log / method = marquardt fiml ;
   run ;
   quit ;
但是sas日志提示error：
NOTE: At OLS Iteration 1 CONVERGE=0.001 Criteria Met.
NOTE: At SUR Iteration 0 CONVERGE=0.001 Criteria Met.
ERROR: The parameter estimates failed to converge for FIML after 29 iterations using CONVERGE=0.001 as the convergence
       criteria.
375     quit ;

好像是参数不收敛？请问为什么会这样？