Maximum Likelihood Estimation of Gamma Jump-diffusion Process

Abstract

The jump diffusion model is a very important model for studying the distribution of Return on Assets. Based on the jump-diffusion models, this paper uses gamma distribution, and selects a representative stock data of China's stock market as a research object, using the N-M method to perform maximum likelihood estimation of the parameters in the model. The result shows that the effect of the data of the simulated high kurtosis of the gamma jump-diffusion model is better than that of the low-kurtosis data.