Gaussian and Poissonian approximations

Goal:

The goal of this project is to illustrate several Gaussian and Poissonian approximations existing in the literature, and the to use them to solve problems arising from statistics. review several methods for simulating the most popular and widely used probability distributions. Then, effective implementations of those techniques will be done and will be used to empirically compute some features (such as median, moments, etc.) of the considered distributions.

Schedule: To be determined with the student(s).

Supervisors: Ivan Nourdin, Diu Tran, Guangqu Zheng.

Difficulty level: Medium level.

Tools: Programs will be coded in Matlab or Scilab.

Results: To be completed at the end of the project.

FSCT -- University of Luxembourg