python中“arch\u模型”和“fit”对值接近0的数据序列的GARCH参数估计

Question

我试图估计一个GARCH（1,1）模型的alpha，beta和omega参数，这个模型的数据集大约有4000个接近于零的值。你知道吗

问题是拟合函数只估计一个和两个参数。我还收到了一个收敛警告。你知道吗

如何拟合并获得更精确的参数估计？你知道吗

returns = [0.01,-0.02,0.0453,0.002, ....]

am = arch_model(returns, mean = 'Zero', vol='Garch', p=1, o=0, q=1, dist='normal')

GARCH_n= am.fit(update_freq=5, disp = 'off')

omega = GARCH_n.params[0]
alpha = GARCH_n.params[1]
beta = GARCH_n.params[2]

/anaconda3/lib/python3.7/site-packages/arch/univariate/base.py:571: ConvergenceWarning: The optimizer returned code 8. The message is: Positive directional derivative for linesearch See scipy.optimize.fmin_slsqp for code meaning.

ConvergenceWarning)