基于连续混合正态分布的期货定价偏差研究

Study on the Bias of Futures Pricing Based on Continuous Mixed Normal Distribution

挖掘期货理论价格和实际价格之间的关系有助于提高期货市场定价效率、发挥期货价格发现功能。基于持有成本定价模型计算期货定价偏差,利用连续混合正态分布模型对定价偏差的分布进行拟合,先采用基于牛顿迭代的极大似然估计法对未知参数进行估计,再进一步利用模拟退火算法对牛顿迭代的结果进行优化。结果发现,模拟退火算法可以有效提高估计精度,连续混合正态分布模型能够更好地拟合期货定价偏差分布。

Mining the relationship between the theoretical price and the actual price of futures will help improve the pricing efficiency of futures market and give play to the discovery function of futures price.The deviation of futures pricing is calculated based on the hold-cost pricing model and the deviation is fitted by the continuous mixed normal distribution model.The unknown parameters are estimated by the maximum likelihood estimation method based on Newton iteration,and then the results of Newton iteration are optimized by the simulated annealing algorithm.The results show that the simulated annealing algorithm can effectively improve the estimation accuracy,and the continuous mixed normal distribution model can fit the deviation distribution of futures pricing better.