Mehmet Cadirci

Research

Research interests

Statistics Group

Education

M.Sc  Mathematics, (University of Sussex, 2016-2017)

Research interests

• Statistics
• Probability Theory
• Shannon-Renyi Entropy
• Kullback Leibler Divergence
• Statistical Inference

Teaching

• Maths Support
• Foundations of Probability (Tutorials)

Thesis

Entropy based on the goodness-of-fit tests for multivariate distributions

This thesis offers a non-parametric test of goodness-of-fit for a class of multivariate generalized Gaussian distributions based on the maximum Shannon entropy principle andthe k-th nearest neighbour distances method of Shannon entropy. It also presents a non parametric test of goodness-of-fit for a classes of multivariate Student and Pearson type II (or Barenblatt ) distributions based on the maximum Rényi entropy principle. Moreover, it introduces three generalizations of von Mises-Fisher distribution on a sphere
and the maximum Shannon entropy principle for them. Based on the L^2-consistency of the k-th nearest neighbour estimate of Shannon entropy. The results are supported by a Monte Carlo simulation.

Supervisors

Publications

There was an error in processing data returned back from the API: Unexpected end of JSON input