各位大侠，帮忙看看这是怎么了，谢谢了。看的头晕眼花了！！运行极大似然估计的提示：
Warning: Gradient must be provided for trust-region algorithm;
  using line-search algorithm instead.
> In fminunc at 347
  In exc at 118
Local minimum possible.
fminunc stopped because the size of the current step is less than
the selected value of the step size tolerance.
<stopping criteria details>

Local minimum possible.
fminunc stopped because it cannot decrease the objective function
along the current search direction.
<stopping criteria details>

Computing finite-difference Hessian using user-supplied objective function.
Likelihood Has Converged
Computing Test Statistics
Warning: Matrix is close to singular or badly scaled.
         Results may be inaccurate. RCOND = 3.111721e-025.
> In exc at 143
Warning: Matrix is close to singular or badly scaled.
         Results may be inaccurate. RCOND = 3.126260e-025.
> In exc at 161
Optimization stopped because the norm of the current step, 5.081653e-005, is
less than options.TolX = 1.000000e+008.
Optimization Metric                                    Options
relative norm(step) =  5.08e-005                TolX =  1e+008 (selected)

Optimization stopped because the objective function cannot be decreased in the
current search direction. Either the predicted change in the objective function,
or the line search interval is less than eps.