Abstract

Characterization of volatile commodity prices with a stochastic jump-diffusion process, where jumps are described by an exponent of Compound Poisson Process. We provide several useful properties for discretized process and analyze parameter fitting algorithm via the moments method. In addition we prove that the distribution cannot be uniquely determined via its moments, as is the case for the lognormal distribution.

中文翻译：

---

对数正态分布的泊松混合

摘要

使用随机跳跃扩散过程来表征波动的商品价格，其中跳跃由复合泊松过程的指数来描述。我们为离散过程提供了几个有用的属性，并通过矩量法分析了参数拟合算法。此外，我们证明了分布不能像偶数对数正态分布一样通过其矩唯一地确定。